# Green Software

A software-engineering discipline focused on reducing the carbon emissions of software through carbon, energy, and hardware efficiency.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## SpikingGamma: Temporally Precise Online SNN Training Through Smoothed Temporal Delays

DevFeed: [SpikingGamma: Temporally Precise Online SNN Training Through Smoothed Temporal Delays](<https://devfeed.tech/articles/spikinggamma-temporally-precise-online-snn-training-through-smoothed-temporal-delays-144872.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2602.01978>)

Author: Roel Koopman, Sebastian Otte, Sander Boht\\'e

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [backpropagation](<https://devfeed.tech/tags/backpropagation.md>), [bank](<https://devfeed.tech/tags/bank.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bptt](<https://devfeed.tech/tags/bptt.md>), [complex](<https://devfeed.tech/tags/complex.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ne](<https://devfeed.tech/tags/cs-ne.md>), [delay](<https://devfeed.tech/tags/delay.md>), [delta](<https://devfeed.tech/tags/delta.md>), [energy](<https://devfeed.tech/tags/energy.md>), [event](<https://devfeed.tech/tags/event.md>), [event-driven](<https://devfeed.tech/tags/event-driven.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [latency](<https://devfeed.tech/tags/latency.md>), [learning](<https://devfeed.tech/tags/learning.md>), [online](<https://devfeed.tech/tags/online.md>), [snn](<https://devfeed.tech/tags/snn.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

SpikingGamma aims to make online training of feedforward spiking neural networks more stable at fine temporal resolution. Neurons keep a compact bank of smoothed-delay states and communicate using sigma-delta spike coding. The method backpropagates online through a continuous reconstruction signal, avoiding surrogate gradients through the discontinuous spike. The abstract reports stable temporal-pattern learning with minimal spiking, competitive accuracy on complex tasks and benchmarks, and robustness to model temporal resolution. It presents SpikingGamma as an alternative to recurrent SNNs trained with surrogate gradients and as a possible route to neuromorphic hardware; the supplied text gives no specific benchmark results or hardware measurements.

### Source excerpt

arXiv:2602.01978v2 Announce Type: replace-cross Abstract: Neuromorphic hardware implementations of Spiking Neural Networks (SNNs) promise energy-efficient, low-latency AI through sparse, event-driven computation. Yet, training SNNs under fine temporal discretization remains challenging, hindering low-latency responsiveness and the mapping of software-trained SNNs to efficient hardware. In current approaches, spiking neurons are modeled as self-recurrent units, embedded into recurrent networks to maintain state over time, and trained with BPTT or RTRL variants based on surrogate gradients. These methods scale poorly with temporal resolution, while online approximations exhibit instability for long sequences and tend to fail at capturing temporal patterns. To address these limitations, we develop SpikingGamma, an SNN architecture in which neurons maintain a compact bank of smoothed-delay states and communicate through sigma-delta spike-coding. We show that in feedforward networks, SpikingGamma supports direct online error backpropagation through the continuous reconstruction signal, avoiding surrogate gradients through the spike discontinuity. This enables stable learning of temporal patterns with minimal spiking and scales feedforward SNNs to complex tasks and benchmarks with competitive accuracy, all while remaining robust to the temporal resolution of the model. Our approach offers both an alternative to recurrent SNNs trained with surrogate gradients, and a novel route for mapping SNNs to neuromorphic hardware.

## Datacentres to create 70% more carbon emissions by 2030, IEA report warns

DevFeed: [Datacentres to create 70% more carbon emissions by 2030, IEA report warns](<https://devfeed.tech/articles/datacentres-to-create-70-more-carbon-emissions-by-2030-iea-report-warns-142058.md>)

Original publisher: [Read original article](<https://www.theguardian.com/world/2026/nov/19/datacentres-to-create-70-more-carbon-emissions-by-2030-iea-report-warns>)

Author: Jillian Ambrose Energy correspondent

Published: 2026-11-19T05:00:18Z

Content type: news

Language: en

Sources: [The Guardian | Technology](<https://devfeed.tech/sources/the-guardian-technology.md>)

Topics: [clean energy data centers](<https://devfeed.tech/topics/clean-energy-data-centers.md>), [nuclear energy for AI](<https://devfeed.tech/topics/nuclear-energy-for-ai.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-artificial-intelligence](<https://devfeed.tech/tags/ai-artificial-intelligence.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [asia-pacific](<https://devfeed.tech/tags/asia-pacific.md>), [business](<https://devfeed.tech/tags/business.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [china](<https://devfeed.tech/tags/china.md>), [cloud-computing](<https://devfeed.tech/tags/cloud-computing.md>), [computing](<https://devfeed.tech/tags/computing.md>), [datacenters-us](<https://devfeed.tech/tags/datacenters-us.md>), [datacentres](<https://devfeed.tech/tags/datacentres.md>), [datacentres-renewable-energy-ai-artificial-intelligence-datacenters-us-fossil-fuels-europe-world](<https://devfeed.tech/tags/datacentres-renewable-energy-ai-artificial-intelligence-datacenters-us-fossil-fuels-europe-world.md>), [electricity](<https://devfeed.tech/tags/electricity.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [energy](<https://devfeed.tech/tags/energy.md>), [environment](<https://devfeed.tech/tags/environment.md>), [europe](<https://devfeed.tech/tags/europe.md>), [fossil-fuels](<https://devfeed.tech/tags/fossil-fuels.md>), [global-expansion](<https://devfeed.tech/tags/global-expansion.md>), [growth](<https://devfeed.tech/tags/growth.md>), [power](<https://devfeed.tech/tags/power.md>), [renewable-energy](<https://devfeed.tech/tags/renewable-energy.md>), [technology-sector](<https://devfeed.tech/tags/technology-sector.md>), [us](<https://devfeed.tech/tags/us.md>), [us-news](<https://devfeed.tech/tags/us-news.md>), [world](<https://devfeed.tech/tags/world.md>), [world-news](<https://devfeed.tech/tags/world-news.md>)

### AI overview

The IEA projects data-centre emissions will rise 70% by 2030 as electricity use doubles, with AI accounting for three-quarters of the increase. It estimates AI data centres will add 350 TWh of annual electricity demand within four years. The expected power mix differs by region: about half of China's AI data-centre electricity will come from coal, while US data centres are expected to rely on gas for about 60%. In the EU, renewables are projected to supply about 70%. Developers are major renewable-energy buyers, but fossil-fuel generation is expected to grow especially quickly in the US and China. The IEA based its forecasts on AI-server shipment data and satellite imagery tracking 93 large AI facilities.

### Source excerpt

Global energy watchdog forecasts huge rise as US and China turn to fossil fuels to power AI growth agendas The world's datacentres will create 70% more carbon emissions within the next four years as the US and China turn to fossil fuels to power their AI growth agendas, according to the world's energy watchdog. The International Energy Agency (IEA) warned that datacentres will consume twice as much electricity by 2030 compared with today, with the global expansion of artificial intelligence accounting for three-quarters of this growth. Continue reading...

## AdaS-ViT: Test-Time Adaptive Routing for Spiking Vision Transformers with Ultra-High Energy Efficiency

DevFeed: [AdaS-ViT: Test-Time Adaptive Routing for Spiking Vision Transformers with Ultra-High Energy Efficiency](<https://devfeed.tech/articles/adas-vit-test-time-adaptive-routing-for-spiking-vision-transformers-with-ultra-high-energy-efficiency-142696.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23728>)

Author: Zecheng Hao, Zihan Huang, Shenghao Xie, Jiyuan Zhang, Zhaofei Yu, Tiejun Huang

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Transformer](<https://devfeed.tech/topics/transformer.md>), [image recognition](<https://devfeed.tech/topics/image-recognition.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>), [Transformers](<https://devfeed.tech/topics/transformers.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [all](<https://devfeed.tech/tags/all.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attention](<https://devfeed.tech/tags/attention.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [building](<https://devfeed.tech/tags/building.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-ne](<https://devfeed.tech/tags/cs-ne.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [energy](<https://devfeed.tech/tags/energy.md>), [energy-efficiency](<https://devfeed.tech/tags/energy-efficiency.md>), [routing](<https://devfeed.tech/tags/routing.md>), [test](<https://devfeed.tech/tags/test.md>), [time](<https://devfeed.tech/tags/time.md>), [transformers](<https://devfeed.tech/tags/transformers.md>), [vision](<https://devfeed.tech/tags/vision.md>), [vision-transformers](<https://devfeed.tech/tags/vision-transformers.md>), [vit](<https://devfeed.tech/tags/vit.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

AdaS-ViT reduces redundant spiking computation by adapting firing precision at test time across temporal, spatial and channel dimensions. Its AdaE-IF module uses attention scores to route salient regions to fine-grained firing patterns and the rest to coarser, lower-energy patterns; S-GSA and S-LGU add selective spike emission at token and channel granularity. A progressive spatio-temporal training curriculum is used to stabilize the routing masks and firing precision. The abstract reports competitive results across benchmarks and 1.02-2.45 mJ per image on ImageNet-1k, with an accuracy-per-energy ratio of 32x-72x.

### Source excerpt

arXiv:2611.23728v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) promise event-driven and energy-efficient vision, yet existing spiking vision transformers (S-ViTs) largely confine spiking tokens to fixed and uniform firing schemes along the temporal, spatial and channel dimensions, whereas suppressing the computational redundancy thus incurred calls for adaptive firing mechanisms that operate jointly across all three axes at test time. To this end, we propose the Adaptive Efficient Integrate-and-Fire (AdaE-IF) model, which consults the attention score of each spiking token and routes salient regions to fine-grained firing patterns while assigning energy-frugal coarse patterns to the remaining regions. Building on AdaE-IF, we further introduce Spiking Gated Self-Attention (S-GSA) and Spiking Local-Gated Unit (S-LGU), which enforce selective spike emission at token and channel granularity. We integrate the aforementioned mechanisms and modules into AdaS-ViT, a test-time adaptive-routing architecture trained with a progressive spatio-temporal curriculum that stabilizes the co-adaptation of firing precision and routing masks. Extensive experiments across benchmarks spanning diverse data scales and modalities demonstrate that AdaS-ViT consistently achieves highly competitive performance. Notably, on ImageNet-1k it consumes only 1.02 to 2.45 millijoules per image and attains an accuracy-per-energy ratio of 32$\times$ to 72$\times$, operating in an economical inference regime and thereby pushing the energy-efficiency boundary further.

## A Cherry-Picking Approach to Large Load Shaping for More Effective Carbon Reduction

DevFeed: [A Cherry-Picking Approach to Large Load Shaping for More Effective Carbon Reduction](<https://devfeed.tech/articles/a-cherry-picking-approach-to-large-load-shaping-for-more-effective-carbon-reduction-141538.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2601.17990>)

Author: Bokan Chen, Raiden Hasegawa, Adriaan Hilbers, Ross Koningstein, Ana Radovanovi\\'c, Utkarsh Shah, Gabriela Volpato, Mohamed Ahmed, Tim Cary, Rod Frowd

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [clean energy data centers](<https://devfeed.tech/topics/clean-energy-data-centers.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [3](<https://devfeed.tech/tags/3.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [accessible](<https://devfeed.tech/tags/accessible.md>), [accounting](<https://devfeed.tech/tags/accounting.md>), [all](<https://devfeed.tech/tags/all.md>), [approach](<https://devfeed.tech/tags/approach.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [best](<https://devfeed.tech/tags/best.md>), [bus](<https://devfeed.tech/tags/bus.md>), [can](<https://devfeed.tech/tags/can.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [co2](<https://devfeed.tech/tags/co2.md>), [co2-emissions](<https://devfeed.tech/tags/co2-emissions.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [effective](<https://devfeed.tech/tags/effective.md>), [large](<https://devfeed.tech/tags/large.md>), [load](<https://devfeed.tech/tags/load.md>), [more](<https://devfeed.tech/tags/more.md>), [reduction](<https://devfeed.tech/tags/reduction.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>)

### AI overview

A daily "cherry-picking" strategy for shifting large flexible loads achieved 2-3 times the annual grid CO₂ savings of static LMP-based shaping, without higher wholesale electricity costs than flat operation, in year-long counterfactuals using a calibrated, nearly 8,900-bus model of ERCOT's day-ahead market. The strategy selects among practicable day-ahead signals using observable grid net demand and nodal minimum LMP, with thresholds learned from historical market data. Although LMP shaping beat other static signals annually, no single signal performed best in every operating condition. Coordinating shifts across two grid nodes increased CO₂ reductions by over 70% compared with temporal-only shifting. The authors also report that region-wide average carbon intensity can raise physical emissions in fossil-heavy zones, supporting locational, price-aware and congestion-aware Scope 2 accounting. These are model-based ERCOT findings.

### Source excerpt

arXiv:2601.17990v2 Announce Type: replace-cross Abstract: Shaping multi-megawatt flexible loads such as data centers alters generator dispatch on the electric grid, affecting system-wide CO2 emissions and wholesale electricity costs. However, evaluating prevalent load-shaping signals - such as grid-average carbon intensity, locational marginal price, renewable generation, or commercial marginal emission estimates - has remained difficult because full-scale market-clearing models and generator bid data are rarely accessible outside system operators. Here we conduct year-long causal dispatch counterfactuals using a calibrated, nearly 8,900-bus replica of ERCOT's day-ahead Security Constrained Unit Commitment and Security Constrained Economic Dispatch market-clearing process across renewable-rich and fossil-dominated zones. We find that while LMP-based shaping outperforms other static signals in annual grid CO2 reductions, no single signal performs best across all operating conditions. Motivated by these insights, we propose an interpretable daily "cherry-picking" strategy that selects among practicable day-ahead signals using observable grid net demand and nodal minimum LMP, with thresholds learnable directly from historical market data. Cherry-picking achieves 2-3 times greater annual grid CO2 savings than static LMP shaping without increasing wholesale electricity cost relative to flat operation. Extending this framework to coordinated spatial and temporal shifting across two grid nodes increases CO2 reductions by over 70% compared to temporal-only shifting. Finally, because shaping load against region-wide average carbon intensity can backfire and raise physical grid emissions in fossil-heavy zones, our findings highlight the need for Scope 2 carbon-accounting frameworks to incorporate locational, price-aware, and congestion-aware signals.

## Identifying and Repairing Energy Smells with Agent Skills

DevFeed: [Identifying and Repairing Energy Smells with Agent Skills](<https://devfeed.tech/articles/identifying-and-repairing-energy-smells-with-agent-skills-139619.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23203>)

Author: Mohammadjavad Mehditabar, Saurabhsingh Rajput, Tushar Sharma

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Green Software](<https://devfeed.tech/topics/green-software.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Static code analysis](<https://devfeed.tech/topics/static-code-analysis.md>)

Tags: [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [computer-science](<https://devfeed.tech/tags/computer-science.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [energy](<https://devfeed.tech/tags/energy.md>), [energy-efficiency](<https://devfeed.tech/tags/energy-efficiency.md>), [python](<https://devfeed.tech/tags/python.md>)

### AI overview

DR. GREENS brings energy-smell checks into Python developers' coding environment, pairing a taxonomy of 12 smells and 65 root causes with repair guidance from 230 measured cases. It combines a static analyzer with an independent verifier to check that attempted repairs preserve behavior and save energy. Across 18 sessions on three open-source repositories, using two models and three configurations, 68.6% of 258 measured repairs saved energy, with a median saving of 24.9%. The full skill found more energy smells with verified savings than a baseline without the taxonomy across all three repositories and both models. These results are limited to the reported evaluation.

### Source excerpt

arXiv:2611.23203v1 Announce Type: new Abstract: Energy smells are inefficient implementations that waste energy. Once code reaches production, these smells become costlier and riskier to fix, so energy efficiency checks should shift left, i.e., move earlier in the development lifecycle, to where code is written. Existing energy smell tools rely on fixed static rules and do not measure energy savings, whereas LLM-based optimizers mostly target execution time and rarely ground their changes in concrete smell definitions. To address both limitations, we present DR. GREENS, an agent skill that detects and repairs energy smells in Python code within the developer's coding environment. The skill grounds the coding agent in our taxonomy of 12 energy smells and 65 root causes, augmented with repair guidance drawn from 230 measured cases. The skill also encapsulates a static analyzer and an independent verifier to confirm behavior preservation and energy saving for each attempted repair. We evaluated DR. GREENS in 18 sessions on three open-source repositories, with two models and three skill configurations. Of the 258 measured repairs, 68.6% saved energy, with a median saving of 24.9%. Compared with a baseline skill that lacks the taxonomy, the full skill found more energy smells with verified savings in all three repositories with both models. DR. GREENS helps developers detect energy hotspots and fix them reliably without altering program behavior, which makes energy-efficient development more feasible.

## Investigating the Impact of CI-Source Sensitivity in Carbon-Aware Resource Management Systems

DevFeed: [Investigating the Impact of CI-Source Sensitivity in Carbon-Aware Resource Management Systems](<https://devfeed.tech/articles/investigating-the-impact-of-ci-source-sensitivity-in-carbon-aware-resource-management-systems-136994.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20830>)

Author: Gon\\c{c}alo Ferreira, Jaime Iglesias Blanco, Mar\\'ia Castrillo, \\'Alvaro L\\'opez Garc\\'ia, Li Wu, Shashikant Ilager

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>), [clean energy data centers](<https://devfeed.tech/topics/clean-energy-data-centers.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-ai](<https://devfeed.tech/tags/artificial-intelligence-ai.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [ci](<https://devfeed.tech/tags/ci.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [energy](<https://devfeed.tech/tags/energy.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [grid](<https://devfeed.tech/tags/grid.md>), [latency](<https://devfeed.tech/tags/latency.md>), [management](<https://devfeed.tech/tags/management.md>), [operational](<https://devfeed.tech/tags/operational.md>), [performance](<https://devfeed.tech/tags/performance.md>), [providers](<https://devfeed.tech/tags/providers.md>), [resource](<https://devfeed.tech/tags/resource.md>), [resource-management](<https://devfeed.tech/tags/resource-management.md>), [source](<https://devfeed.tech/tags/source.md>)

### AI overview

Using Wattnet and ElectricityMaps traces across five Central European zones, the study evaluates how carbon-intensity (CI) signal differences affect carbon-aware placement. Its ESCAPE framework tests provider switching and controlled CI perturbations in a reproduced setting, using CarbonEdge to measure placement decisions, carbon proxy, energy use, and latency. Switching CI sources changed the dominant placement site in 43.50% of cases and altered reported operational outcomes, despite high rank correlation between sources. The authors argue that CI uncertainty should be accounted for explicitly in resource-allocation decisions.

### Source excerpt

arXiv:2611.20830v1 Announce Type: new Abstract: The sustainable growth of data centres increasingly depends on Resource-Management Systems (RMSs) that aim to reduce carbon emissions of computing workloads without degrading performance. This need is intensified by the rise of Artificial Intelligence (AI) workloads, which demand exponentially growing amounts of compute and energy across geographically distributed infrastructure. Recent carbon-aware RMSs exploit temporal and spatial variation in grid Carbon Intensity (CI) to shift workloads towards lower-carbon periods or locations. In practice, CI estimates and forecasts can be inaccurate and uncertain, and CI providers' methods differ substantially. Such discrepancies may have a significant impact on RMS placement decision-making, raising concerns about the fragility of existing solutions. Thus, in this work, we ask how discrepancies between plausible CI estimates propagate into resource-management decisions and operational outcomes. To answer this question, we harmonise and characterise CI traces from Wattnet and ElectricityMaps across five Central European zones. We then propose our evaluation framework: External CI Signal Characterisation And Perturbation Evaluation (ESCAPE), which assesses provider switching and controlled CI perturbations in a reproduced placement setting. We implement our framework using CarbonEdge as a use case, and measure changes in placement decisions and operational outcomes, such as carbon proxy, energy use, and latency. Our results show that switching CI-source changes the dominant placement site in 43.50% cases, and alters reported operational outcomes. These changes occur despite high rank correlation and structured disagreement between CI-sources. This observed sensitivity to CI-source choice motivates robustness-aware carbon-aware placement, in which CI uncertainty should be explicitly accounted for in resource-allocation decisions.

## Measuring and Optimizing Energy Efficiency in ICT: A Multi-vocal Literature Review on Data Centers, Cloud Computing, and LLM-Driven Code Optimization

DevFeed: [Measuring and Optimizing Energy Efficiency in ICT: A Multi-vocal Literature Review on Data Centers, Cloud Computing, and LLM-Driven Code Optimization](<https://devfeed.tech/articles/measuring-and-optimizing-energy-efficiency-in-ict-a-multi-vocal-literature-review-on-data-centers-cloud-computing-and-llm-driven-code-optimization-137962.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18576>)

Author: Tobias B\\"ohm, Benjamin Weigell, Ezgi Sarikayak, Philipp M. Z\\"ahl, Tina Vartziotis, Simon Hornung, Julien Siebert, Anika Hennig, Bernhard Bauer, Andreas Biesdorf

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>), [clean energy data centers](<https://devfeed.tech/topics/clean-energy-data-centers.md>), [data centers](<https://devfeed.tech/topics/data-centers.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Cloud Architecture](<https://devfeed.tech/topics/cloud-architecture.md>), [reproducibility](<https://devfeed.tech/topics/reproducibility.md>)

Tags: [cloud-computing](<https://devfeed.tech/tags/cloud-computing.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [container](<https://devfeed.tech/tags/container.md>), [containers](<https://devfeed.tech/tags/containers.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [energy](<https://devfeed.tech/tags/energy.md>), [energy-efficiency](<https://devfeed.tech/tags/energy-efficiency.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [literature](<https://devfeed.tech/tags/literature.md>), [llms](<https://devfeed.tech/tags/llms.md>), [measuring](<https://devfeed.tech/tags/measuring.md>), [memory](<https://devfeed.tech/tags/memory.md>), [network](<https://devfeed.tech/tags/network.md>), [optimizing](<https://devfeed.tech/tags/optimizing.md>), [python](<https://devfeed.tech/tags/python.md>), [resource-management](<https://devfeed.tech/tags/resource-management.md>), [review](<https://devfeed.tech/tags/review.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [software](<https://devfeed.tech/tags/software.md>), [system-design](<https://devfeed.tech/tags/system-design.md>)

### AI overview

This multi-vocal review synthesizes 181 sources published or collected from 2010-2025 on measuring and reducing energy use in ICT, with emphasis on data centers and cloud computing. It organizes sustainability measures by domain--power and energy, efficiency, and environmental impact--and by component scale, from applications to system-of-systems. The reviewed optimization approaches include dynamic power and resource management, VM and container consolidation, energy-aware design, and cross-layer methods. For LLM-assisted code generation and transformation, most studies focus on Python and report runtime and memory; fewer directly measure energy. The review identifies gaps in vendor-neutral telemetry, consistent reporting, network metrics, and unified cross-layer optimization, which limit reproducibility and comparison.

### Source excerpt

arXiv:2611.18576v1 Announce Type: new Abstract: Rapid growth in Information and Communication Technology (ICT) increases electricity use and environmental impact. Addressing this challenge requires a systematic, software-centric view of how energy and related sustainability attributes are measured, reported, and improved. We present a comprehensive Multi-vocal Literature Review (MLR) integrating peer-reviewed and gray literature to map current practice in measuring and optimizing energy use in ICT software, with emphasis on data centers and cloud computing environments (DCCCEs). First, we synthesize how sustainability is measured across ICT by proposing a taxonomy organized along metric domains (power/energy, energy efficiency, environmental impact) and component granularity (from applications, to containers/VMs, and system-of-systems levels). We summarize measurement approaches and the tooling landscape that implements them. Second, we review optimization strategies at the software and system levels, covering dynamic power and resource management, VM/container consolidation, energy-aware software and system design, and cross-layer, system-wide methods relevant to DCCCEs. Third, we examine how large language models (LLMs) are applied to code generation and transformation for resource-efficient software, noting that most studies target code generation (predominantly in Python) and evaluate runtime and memory, with fewer works directly reporting energy. Hardware- and network-level telemetry are treated as data sources for software-level analysis. We identify gaps in vendor-neutral telemetry, consistent measurement and reporting practices, network-level metrics, and unified, cross-layer optimization frameworks, and outline directions for improving reproducibility and comparability. We screened 635 records (2010-2025) and included 181 sources (122 peer-reviewed, 59 gray).

## ERGo: Energy-Efficient Hybrid Graph Neural Network Training on Processing-In-Memory Architectures

DevFeed: [ERGo: Energy-Efficient Hybrid Graph Neural Network Training on Processing-In-Memory Architectures](<https://devfeed.tech/articles/ergo-energy-efficient-hybrid-graph-neural-network-training-on-processing-in-memory-architectures-135781.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17478>)

Author: Pratyush Dhingra, Chibuike E. Ugwu, Janardhan Rao Doppa, Partha Pratim Pande

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Deep neural networks](<https://devfeed.tech/topics/deep-neural-networks.md>), [High-Performance Computing](<https://devfeed.tech/topics/high-performance-computing.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [based](<https://devfeed.tech/tags/based.md>), [can](<https://devfeed.tech/tags/can.md>), [cells](<https://devfeed.tech/tags/cells.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [energy](<https://devfeed.tech/tags/energy.md>), [ergo](<https://devfeed.tech/tags/ergo.md>), [graph](<https://devfeed.tech/tags/graph.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [hybrid-graph](<https://devfeed.tech/tags/hybrid-graph.md>), [memory](<https://devfeed.tech/tags/memory.md>), [network](<https://devfeed.tech/tags/network.md>), [neural](<https://devfeed.tech/tags/neural.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [processing](<https://devfeed.tech/tags/processing.md>), [processing-in-memory](<https://devfeed.tech/tags/processing-in-memory.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

ERGo reduces costly off-chip access during GNN training on processing-in-memory (PIM) architectures by automatically switching from full-parameter training to a parameter-efficient phase that represents weights at low rank. The abstract reports negligible loss in predictive accuracy, up to 3.15x speedup, and 10.5x greater energy efficiency than conventional full-parameter training on a PIM platform. On heterogeneous NVM-SRAM systems, which use NVM for forward passes and SRAM for backward passes, ERGo freezes weights in the parameter-efficient phase, reducing NVM writes associated with updates. Experiments report up to 33x longer architecture lifetime than the full-parameter implementation. These are reported maxima; the excerpt gives no experimental conditions or broader evaluation details.

### Source excerpt

arXiv:2611.17478v1 Announce Type: new Abstract: Processing-in-memory (PIM) has been proposed as an alternative computing paradigm for training Deep Neural Networks, including Graph Neural Networks (GNNs). Despite these advancements, training GNN workloads on PIM devices necessitates off-chip memory access. This off-chip access is expensive in terms of performance and energy, thereby impacting the overall energy efficiency of the training process on PIM platforms. In this paper, we propose a novel hybrid training framework called ERGo that automatically switches from a full-parameter phase to a parameter-efficient phase during the training process with negligible loss in predictive accuracy. The parameter-efficient phase employs low-rank representations of GNN weights, effectively reducing the number of trainable parameters. This helps in reducing the off-chip access during the end-to-end training process on PIM architectures, leading to notable improvements in both performance and energy efficiency. ERGo outperforms the conventional full-parameter GNN training on a PIM-based platform by up to 3.15x in speedup and enhances energy efficiency by 10.5x. Furthermore, ERGo offers additional advantages when utilized on heterogeneous architectures incorporating non-volatile memory (NVM) and static random-access memory (SRAM). Training on the heterogeneous NVM-SRAM architecture typically utilizes NVM for the forward-pass and SRAM for the backward-pass. However, NVM cells suffer from low device endurance and repeated write operations due to weight updates can lead to poor lifetime. ERGo improves the lifetime of NVM devices by freezing the weights and preventing weight updates in the parameter-efficient phase. Experimental results demonstrate that ERGo improves the lifetime of heterogeneous NVM-SRAM architecture by up to 33x in comparison to full-parameter implementation.

## Measured from the feed: the unsustainable growth of AI video generation

DevFeed: [Measured from the feed: the unsustainable growth of AI video generation](<https://devfeed.tech/articles/measured-from-the-feed-the-unsustainable-growth-of-ai-video-generation-135151.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17938>)

Author: Tristan Coignion, Aur\\'elie Bugeau, Gael Guennebaud, Anne-Laure Ligozat

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-et](<https://devfeed.tech/tags/cs-et.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [growth](<https://devfeed.tech/tags/growth.md>), [video](<https://devfeed.tech/tags/video.md>), [video-generation](<https://devfeed.tech/tags/video-generation.md>)

### AI overview

Providers rarely disclose video volumes or energy needs, so the authors measured yearly output from two commercial text-to-video platforms and modeled one service's footprint from training through storage. Their projections indicate that continued growth could raise emissions nearly 75-fold by 2030 despite efficiency improvements; holding usage at 2026 levels would let those improvements reduce emissions by about two-fifths. The estimates are a conservative lower bound, covering one service among many.

### Source excerpt

arXiv:2611.17938v1 Announce Type: new Abstract: Text-to-video generation runs at commercial scale, but its broader environmental impacts remain, to our knowledge, understudied. Providers rarely disclose video volumes or energy needs; we measured the yearly video output of two commercial platforms and built a prospective model of such services' absolute footprint from training to storage. Our projections suggest that reducing emissions depends on both limiting growth in video generation and achieving substantial efficiency gains. Under continued growth, emissions rise nearly seventy-five-fold by 2030 despite technological improvements. When usage remains at 2026 levels, the same improvements reduce emissions by about two-fifths. These estimates are a conservative lower bound: they cover one AI service among many; other services and uses would push the total higher.

## Sustainable Federated Fine-Tuning with LoRA: Environmental Impact and Performance Footprint

DevFeed: [Sustainable Federated Fine-Tuning with LoRA: Environmental Impact and Performance Footprint](<https://devfeed.tech/articles/sustainable-federated-fine-tuning-with-lora-environmental-impact-and-performance-footprint-131590.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16856>)

Author: Pedro Augusto Londe Ribeiro, Rodrigo Moreira, Larissa Ferreira Rodrigues Moreira, Joberto S. B. Martins, Tereza C. Carvalho, Fl\\'avio de Oliveira Silva

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>), [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [lora](<https://devfeed.tech/topics/lora.md>), [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [peft](<https://devfeed.tech/topics/peft.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>)

Tags: [a100](<https://devfeed.tech/tags/a100.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [energy](<https://devfeed.tech/tags/energy.md>), [energy-consumption](<https://devfeed.tech/tags/energy-consumption.md>), [environmental-impact](<https://devfeed.tech/tags/environmental-impact.md>), [federated](<https://devfeed.tech/tags/federated.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [llms](<https://devfeed.tech/tags/llms.md>), [local](<https://devfeed.tech/tags/local.md>), [lora](<https://devfeed.tech/tags/lora.md>), [models](<https://devfeed.tech/tags/models.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [peft](<https://devfeed.tech/tags/peft.md>), [performance](<https://devfeed.tech/tags/performance.md>), [rtx](<https://devfeed.tech/tags/rtx.md>)

### AI overview

In the evaluated federated LoRA fine-tuning setup, using fewer local steps achieved comparable accuracy on NVIDIA A40 and RTX 6000 Ada GPUs while consuming roughly 6-8 times less energy and delivering higher accuracy per kWh. The study tested 135M and 360M models at 10 or 100 local steps across A40, RTX 6000 Ada, and A100 GPUs, tracking energy and estimated CO₂-equivalent emissions with CodeCarbon. Within those tested ranges, local steps accounted for 84.8-91.2% of the variation in energy and emissions. The findings support smaller local-step budgets in this setting; the excerpt does not report the same accuracy-energy result for A100.

### Source excerpt

arXiv:2611.16856v1 Announce Type: cross Abstract: Federated Learning (FL) with Parameter-Efficient Fine-Tuning (PEFT) enables efficient adaptation of Large Language Models (LLMs), yet its energy and carbon costs across hardware remain poorly understood. We evaluated federated Low-Rank Adaptation (LoRA) fine-tuning on NVIDIA A40, RTX 6000 Ada, and A100 GPUs using a $2^2$ full factorial design with 135M/360M models and 10/100 local steps. CodeCarbon tracked energy and estimated CO$_2$-equivalent emissions. Descriptive allocation of variation assigned 84.8-91.2% of energy and emissions variation to local steps within these ranges. On A40 and RTX 6000 Ada, configurations with fewer steps achieved comparable accuracy with roughly 6-8-fold lower energy consumption and higher accuracy per kWh. These findings support smaller local budgets for energy-efficient federated fine-tuning within the evaluated setting.

## Toward Sustainable Agentic AI: Carbon Tradeoffs Across Iterative Self-Refinement and Tool-Augmented Coding

DevFeed: [Toward Sustainable Agentic AI: Carbon Tradeoffs Across Iterative Self-Refinement and Tool-Augmented Coding](<https://devfeed.tech/articles/toward-sustainable-agentic-ai-carbon-tradeoffs-across-iterative-self-refinement-and-tool-augmented-coding-126237.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.12128>)

Author: Boris Ruf, Adrien de Mailly Nesle, Marcin Detyniecki

Published: 2026-11-10T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [coding](<https://devfeed.tech/tags/coding.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [tools](<https://devfeed.tech/tags/tools.md>), [tradeoffs](<https://devfeed.tech/tags/tradeoffs.md>)

### AI overview

The study finds that agentic methods can trade lower error rates or higher task success for greater estimated emissions, with results depending on the task and metric. On two MATH splits, three GPT-4.1-mini self-refinement steps brought accuracy to within one percentage point of GPT-4.1 single-pass, while nearly tripling carbon versus the cheaper single-pass baseline; under the study's token-based scenario, emissions remained below GPT-4.1's. On SWE-bench Lite, GPT-5.3-codex had the highest resolution rate in the sample (81.2%), followed by Claude Opus 4.6 (68.9%) and GPT-4.1-mini (25.0%). GPT-4.1-mini had the lowest estimated carbon and cost per resolved task, while GPT-5.3-codex resolved substantially more tasks. Estimates count output-token inference only: they exclude tool execution and prompt tokens, which account for over 99% of Study 2 tokens, so they are lower bounds on total footprint.

### Source excerpt

arXiv:2611.12128v1 Announce Type: new Abstract: Agentic language model systems can improve performance either by iterating on their own outputs or by using external tools in grounded environments. While these strategies can reduce error rates and substitute for larger models in some settings, their environmental cost remains relatively underexplored. We present two complementary empirical studies that estimate the energy and carbon footprint of agentic AI across settings of increasing complexity. Study~1 evaluates iterative verbal self-refinement: GPT-4.1-mini at $k = 1$--$5$ steps versus a GPT-4.1 single-pass baseline on two MATH benchmark splits. Study~2 evaluates tool-augmented agentic coding: GPT-4.1-mini, Claude Opus~4.6, and GPT-5.3-codex on SWE-bench Lite, where agents operate inside Docker-isolated environments with access to code execution and file editing tools. In Study~1, $k=3$ refinements close a 16-percentage-point accuracy gap to within 1~point, but nearly triple the carbon footprint relative to the cheap single-pass baseline while remaining below the GPT-4.1 single-pass baseline under the current token-based carbon scenario. In Study~2, GPT-5.3-codex achieves the highest resolution rate in this sample (81.2\%), ahead of Claude Opus~4.6 (68.9\%) and GPT-4.1-mini (25.0\%), but resolved-task-normalized efficiency remains mixed: GPT-4.1-mini is lowest on estimated carbon and cost per resolved task, while GPT-5.3-codex delivers substantially higher task success. All carbon estimates cover output-token inference only; prompt tokens, which exceed 99\% of tokens in Study~2, and tool execution are not charged, so the figures are lower bounds on the full agentic footprint.

## Towards Sustainable Federated Learning via Carbon-Aware Client Selection

DevFeed: [Towards Sustainable Federated Learning via Carbon-Aware Client Selection](<https://devfeed.tech/articles/towards-sustainable-federated-learning-via-carbon-aware-client-selection-123696.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09552>)

Author: Wentao Gao, Omid Tavallaie, Albert Y. Zomaya

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>), [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [distributed-training](<https://devfeed.tech/topics/distributed-training.md>)

Tags: [carbon](<https://devfeed.tech/tags/carbon.md>), [carbon-footprint](<https://devfeed.tech/tags/carbon-footprint.md>), [charging](<https://devfeed.tech/tags/charging.md>), [client](<https://devfeed.tech/tags/client.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [energy](<https://devfeed.tech/tags/energy.md>), [fairness](<https://devfeed.tech/tags/fairness.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [google-pixel](<https://devfeed.tech/tags/google-pixel.md>), [mobile-devices](<https://devfeed.tech/tags/mobile-devices.md>), [performance](<https://devfeed.tech/tags/performance.md>), [selection](<https://devfeed.tech/tags/selection.md>), [wi-fi](<https://devfeed.tech/tags/wi-fi.md>)

### AI overview

CA-FCS selects federated learning clients to reduce carbon emissions from local training, accounting for hourly electricity carbon intensity alongside energy use. It estimates client emissions with an energy model based on empirical measurements from Google Pixel smartphones. Because repeatedly choosing low-carbon clients could reduce data diversity and harm accuracy, especially with non-IID data, the strategy also incorporates fairness. Experiments model mobile client availability constraints such as charging status and Wi-Fi connectivity. The authors report up to 46% lower client-side carbon emissions while maintaining competitive model accuracy.

### Source excerpt

arXiv:2611.09552v1 Announce Type: new Abstract: The Information/Communication Technology (ICT) industry is severely challenging the global environment due to the sharply rising carbon emissions generated by machine learning (ML) workloads. Federated Learning (FL) is one of the prominent distributed ML systems used in applications with billions of client devices, such as Google Gboard and Apple Siri. Nearly half of the total carbon footprint in FL originates from client-side computation during local training. However, existing client selection strategies in FL primarily focus on minimizing energy consumption rather than carbon emissions, despite the fact that carbon impact depends not only on computational load but also on the underlying carbon intensity of the energy source. In this paper, we address this gap by proposing a carbon-aware fair client selection strategy (CA-FCS) designed to minimize the carbon emissions associated with model training on client devices. In contrast to existing approaches for reducing carbon emissions in FL, we incorporate hourly carbon intensity and a realistic energy consumption model developed using empirical measurements from Google Pixel smartphones to estimate client-side carbon emissions in FL. Since repeatedly selecting low-carbon clients may reduce data diversity and degrade global model performance, particularly under non-independent and identically distributed (non-IID) data settings, CA-FCS incorporates fairness into client selection to mitigate this issue. We conduct extensive experiments under realistic FL settings for mobile devices, where client participation is constrained by device availability conditions, such as charging status and Wi-Fi connectivity. The results demonstrate that our method reduces client-side carbon emissions by up to 46% while maintaining competitive model accuracy.

## Data Centers are Being Powered By Giant Gas Plants, Possibly Increasing Carbon Pollution for Decades

DevFeed: [Data Centers are Being Powered By Giant Gas Plants, Possibly Increasing Carbon Pollution for Decades](<https://devfeed.tech/articles/data-centers-are-being-powered-by-giant-gas-plants-possibly-increasing-carbon-pollution-for-decades-122309.md>)

Original publisher: [Read original article](<https://hardware.slashdot.org/story/26/11/07/2153213/data-centers-are-being-powered-by-giant-gas-plants-possibly-increasing-carbon-pollution-for-decades>)

Author: EditorDavid

Published: 2026-11-07T22:15:00Z

Content type: news

Language: en

Sources: [Slashdot](<https://devfeed.tech/sources/slashdot.md>)

Topics: [clean energy data centers](<https://devfeed.tech/topics/clean-energy-data-centers.md>), [data centers](<https://devfeed.tech/topics/data-centers.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [energy](<https://devfeed.tech/tags/energy.md>), [gas](<https://devfeed.tech/tags/gas.md>), [geothermal](<https://devfeed.tech/tags/geothermal.md>), [lock](<https://devfeed.tech/tags/lock.md>), [plants](<https://devfeed.tech/tags/plants.md>), [pollution](<https://devfeed.tech/tags/pollution.md>), [power](<https://devfeed.tech/tags/power.md>), [power-plants](<https://devfeed.tech/tags/power-plants.md>), [solar](<https://devfeed.tech/tags/solar.md>), [tech](<https://devfeed.tech/tags/tech.md>)

### AI overview

The excerpt reports that AI and cloud data center demand is driving construction of large gas-fired power plants that could lock in substantial emissions for decades. An analysis cited by the Washington Post projects that tech's share of global carbon emissions could grow as much as fivefold from 2020 to 2030; Allianz estimates data center emissions could double to 643 million tons of CO₂ annually. Examples include two Amazon-backed gas projects in Texas and Pennsylvania, which the article says would emit more than the Alabama coal plant cited for comparison, and a planned Ohio campus supporting OpenAI that is described as using more gas power than the Microsoft and Google projects combined. Companies say the emissions rise is temporary, maintain net-zero commitments and point to clean-energy investments and accounting that partly offsets gas emissions. Amazon's reported carbon footprint was 80.85 million metric tons last year, 58% above when its CEO pledged to shrink it.

### Source excerpt

Rather than racing toward their net-zero targets, Amazon and other AI/cloud computing companies "are driving emissions sharply higher," reports the Washington Post: To support their data centers, tech firms are driving construction of a new generation of supersized, gas-fired power plants that could lock in hundreds of millions of tons of climate pollution for decades to come, according to corporate disclosures and an analysis conducted for The Post by a researcher at the Harvard T.H. Chan School of Public Health. Industry estimates show these projects have put the tech sector on course to grow from a modest driver of industrial carbon pollution into one of the world's biggest emitters of greenhouse gases. Some anticipate that its share of global carbon emissions will increase as much as fivefold from 2020 to 2030. That would leave the tech industry churning out more than half the climate pollution created by global aviation or shipping -- sectors long associated with driving warming... Already, Amazon's carbon footprint reached 80.85 million metric tons last year -- 58% larger than when [Amazon CEO Jeff] Bezos pledged to shrink it. The company has veered far from the path laid out in the Paris agreement, which would have emissions falling steeply by now and dropping to 43% below 2019 levels by 2030. The tech companies say in corporate disclosures and public statements that they remain committed to their net zero targets, and they suggest the emissions surge is temporary -- to be mitigated down the road, when new energy technologies enable the data centers to run cleaner and more efficiently. They also stress that they continue to invest in clean energy and rank as some of the world's biggest consumers of it. With some complicated accounting maneuvers and carbon credit purchases, their solar, wind and geothermal installations partly cancel out their gas emissions, according to corporate disclosures. A June report from international insurance/asset management Allianz fo

## We organized Sustainability Month. Here's what we learned. 🌱

DevFeed: [We organized Sustainability Month. Here's what we learned. 🌱](<https://devfeed.tech/articles/we-organized-sustainability-month-here-s-what-we-learned-122217.md>)

Original publisher: [Read original article](<https://www.cncf.io/blog/2026/11/07/we-organized-sustainability-month-heres-what-we-learned-%f0%9f%8c%b1/>)

Author: Elif Samedin - CNCF Ambassador | Diana Todea - CNCF Ambassador, Kepler maintainer, TAG Operational Resilience Lead

Published: 2026-11-07T12:30:00Z

Content type: article

Language: en

Sources: [Cloud Native Computing Foundation](<https://devfeed.tech/sources/cloud-native-computing-foundation.md>)

Topics: [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>), [experience report](<https://devfeed.tech/topics/experience-report.md>), [eBPF](<https://devfeed.tech/topics/ebpf.md>), [observability](<https://devfeed.tech/topics/observability.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [Hackathon-Organiser](<https://devfeed.tech/topics/hackathon-organiser.md>)

Tags: [blog](<https://devfeed.tech/tags/blog.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [cloud-native-ecosystem](<https://devfeed.tech/tags/cloud-native-ecosystem.md>), [cncf](<https://devfeed.tech/tags/cncf.md>), [community](<https://devfeed.tech/tags/community.md>), [community-events](<https://devfeed.tech/tags/community-events.md>), [computing](<https://devfeed.tech/tags/computing.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [data-center-efficiency](<https://devfeed.tech/tags/data-center-efficiency.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [ebpf](<https://devfeed.tech/tags/ebpf.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [energy](<https://devfeed.tech/tags/energy.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [environmental-sustainability](<https://devfeed.tech/tags/environmental-sustainability.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [observability](<https://devfeed.tech/tags/observability.md>), [sustainability](<https://devfeed.tech/tags/sustainability.md>)

### AI overview

Cloud Native Sustainability Month showed how environmental sustainability connects to everyday engineering choices, including Kubernetes resource allocation, CPU use, GPU efficiency, carbon observability with OpenTelemetry, eBPF, energy metrics and data center efficiency. The organizers' main takeaway is that engineers need not be sustainability experts to participate: they can question workload resource use, explore projects such as the CNCF incubating project Kepler, and share experiments. Open source contributors can help through code, documentation, testing or community discussion; organizers can start with a lightning talk or meetup discussion. The article presents community events as a way to learn and exchange ideas, while acknowledging that the organizers do not have all the answers.

### Source excerpt

What do Kubernetes resource allocation, eBPF, carbon observability, and GPUs have in common? Quite a lot, actually. Especially when you start looking at them through the lens of environmental sustainability. This October, we brought these conversations...

## Tug of Watts: A study on the Energy - Accuracy Trade-off of Large Language Models on Medical Question Answering Tasks

DevFeed: [Tug of Watts: A study on the Energy - Accuracy Trade-off of Large Language Models on Medical Question Answering Tasks](<https://devfeed.tech/articles/tug-of-watts-a-study-on-the-energy-accuracy-trade-off-of-large-language-models-on-medical-question-answering-tasks-115394.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.02889>)

Author: Viju Sudhi, Giulio Billi, Andreea Scrob, Regina Stodden, Philipp Cimiano

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [energy](<https://devfeed.tech/tags/energy.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [medical](<https://devfeed.tech/tags/medical.md>), [trade](<https://devfeed.tech/tags/trade.md>)

### AI overview

The study evaluates energy use and accuracy for 13 language models from three model families, ranging from 270M to 14B parameters, on medical question-answering tasks in the OpenMedical-LLM leaderboard. It describes ways to estimate energy consumption and emissions, and argues that separate energy and accuracy figures are insufficient for assessing trade-offs: practitioners need to construct and interpret joint metrics for each task. The abstract does not provide specific model rankings or measured results.

### Source excerpt

arXiv:2611.02889v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in medical question answering (QA) systems. While recent works aim at incrementally improving the downstream task accuracy, an empirical estimation of the models' energy consumption and the associated carbon footprints is often overlooked. In this study, we demonstrate how practitioners can estimate energy consumption and arrive at reliable emission estimates for medical QA tasks available in the OpenMedical-LLM leaderboard by investigating 13 LLMs from 3 model families ranging from 270M to 14B parameters. We discuss how one can critically interpret energy versus accuracy trade-offs for a set of models for a given task. With this work, we underline that reporting disjoint energy and accuracy metrics alone does not suffice for careful trade-off assessments, but it also demands systematic construction and interpretation of joint trade-off metrics. We envisage such studies aiding practitioners in adopting better and more efficient models for their task and helping them become active participants in building sustainable LLM pipelines.

## 3D Integration Reduces Embodied-Emissions Impact Of GPU Scaling (imec, VUB)

DevFeed: [3D Integration Reduces Embodied-Emissions Impact Of GPU Scaling (imec, VUB)](<https://devfeed.tech/articles/3d-integration-reduces-embodied-emissions-impact-of-gpu-scaling-imec-vub-115780.md>)

Original publisher: [Read original article](<https://semiengineering.com/3d-integration-reduces-embodied-emissions-impact-of-gpu-scaling-imec-vub/>)

Author: Technical Paper Link

Published: 2026-11-02T20:00:12Z

Content type: article

Language: en

Sources: [Semiconductor Engineering](<https://devfeed.tech/sources/semiconductor-engineering.md>)

Topics: [Chip design](<https://devfeed.tech/topics/chip-design.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>)

Tags: [2-5d](<https://devfeed.tech/tags/2-5d.md>), [3d](<https://devfeed.tech/tags/3d.md>), [3d-integration](<https://devfeed.tech/tags/3d-integration.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [advanced-packaging](<https://devfeed.tech/tags/advanced-packaging.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-accelerators](<https://devfeed.tech/tags/ai-accelerators.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [change](<https://devfeed.tech/tags/change.md>), [chiplets](<https://devfeed.tech/tags/chiplets.md>), [climate](<https://devfeed.tech/tags/climate.md>), [climate-change](<https://devfeed.tech/tags/climate-change.md>), [compute](<https://devfeed.tech/tags/compute.md>), [compute-resources](<https://devfeed.tech/tags/compute-resources.md>), [data](<https://devfeed.tech/tags/data.md>), [embodied-emissions](<https://devfeed.tech/tags/embodied-emissions.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [hbm](<https://devfeed.tech/tags/hbm.md>), [heterogeneous-integration](<https://devfeed.tech/tags/heterogeneous-integration.md>), [high-bandwidth-memory](<https://devfeed.tech/tags/high-bandwidth-memory.md>), [imec](<https://devfeed.tech/tags/imec.md>), [imec-netzero](<https://devfeed.tech/tags/imec-netzero.md>), [impact](<https://devfeed.tech/tags/impact.md>), [integration](<https://devfeed.tech/tags/integration.md>), [packaging](<https://devfeed.tech/tags/packaging.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [semiconductor-sustainability](<https://devfeed.tech/tags/semiconductor-sustainability.md>), [technical-papers](<https://devfeed.tech/tags/technical-papers.md>), [vrije-universiteit-brussel](<https://devfeed.tech/tags/vrije-universiteit-brussel.md>)

### AI overview

Using imec's netzero modeling platform, researchers estimated embodied emissions for chiplet-based GPUs with doubled compute units and HBM capacity. The modeled 3D-scaled system increased embodied emissions by 89%, compared with 141% for 2.5D scaling, suggesting 3D integration can limit the emissions increase from GPU scaling. The excerpt does not specify the underlying model assumptions or other environmental impacts.

### Source excerpt

Researchers at imec and Vrije Universiteit Brussels published "Embodied Emissions of 2.5D and 3D Scaling in Chipletized GPUs for Low-Carbon AI." Abstract "GPU compute resources are scaling to support growing AI workloads, leading to further rises in the climate change impact of hyperscale data centers that rely on high-performance GPUs. To model how packaging decisions... " read more The post 3D Integration Reduces Embodied-Emissions Impact Of GPU Scaling (imec, VUB) appeared first on Semiconductor Engineering.

## Aceso: Latency-Aware Geo-Distribution of Microservices for Cost-Effective Carbon Reduction

DevFeed: [Aceso: Latency-Aware Geo-Distribution of Microservices for Cost-Effective Carbon Reduction](<https://devfeed.tech/articles/aceso-latency-aware-geo-distribution-of-microservices-for-cost-effective-carbon-reduction-107552.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2603.10768>)

Author: Georgia Christofidi, Francisco \\'Alvarez-Terribas, Ioannis Roumpos, Nicolas Kourtellis, Jesus Oma\\~na Iglesias, Thaleia Dimitra Doudali

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [Green Software](<https://devfeed.tech/topics/green-software.md>), [Microservices](<https://devfeed.tech/topics/microservices.md>), [resource orchestration](<https://devfeed.tech/topics/resource-orchestration.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>), [cloud cost management](<https://devfeed.tech/topics/cloud-cost-management.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-computing](<https://devfeed.tech/tags/cloud-computing.md>), [cost](<https://devfeed.tech/tags/cost.md>), [country](<https://devfeed.tech/tags/country.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [data-sovereignty](<https://devfeed.tech/tags/data-sovereignty.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [geo](<https://devfeed.tech/tags/geo.md>), [global](<https://devfeed.tech/tags/global.md>), [hpc](<https://devfeed.tech/tags/hpc.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [latency](<https://devfeed.tech/tags/latency.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [mitigation](<https://devfeed.tech/tags/mitigation.md>), [reduction](<https://devfeed.tech/tags/reduction.md>)

### AI overview

Aceso places microservices across geographically constrained regions to balance carbon emissions, operational cost, and latency. Its scalable optimization prunes the search space and adapts placement to changing workloads and carbon intensity. In a real-world deployment, compared with a static deployment within one country, it reduced emissions by up to 37.4% and operational cost by up to 3.36% on average across days while maintaining latency targets. The supplied abstract does not detail the deployment or evaluation methodology.

### Source excerpt

arXiv:2603.10768v3 Announce Type: replace Abstract: Microservices are a dominant architecture in cloud computing, offering scalability and modularity, but also posing complex deployment challenges. As data centers contribute significantly to global carbon emissions, carbon-aware scheduling is a promising mitigation strategy. However, most existing solutions target batch, HPC, or serverless workloads and assume global-scale infrastructure. Such an assumption does not hold for many regional small to medium-sized enterprises (SMEs) with microservice applications, due to geographic, cost, and data sovereignty constraints. In this paper, we present Aceso, an Adaptive Carbon- and Efficiency-aware placement for microservices that considers carbon, cost, and latency constraints. Aceso dynamically places microservices across geographically constrained regions using a scalable optimization with insight-based search space pruning techniques. Evaluation on a real-world deployment shows that Aceso adapts to real-time changes in workload and carbon intensity and reduces carbon emissions by up to 37.4% and operational cost by up to 3.36%, on average across days, compared to a static deployment within a single country, while maintaining the application's latency targets. In this way, Aceso enables carbon- and cost-aware microservice deployment for latency-sensitive applications in regionally limited infrastructures.

## How to Make Artificial Intelligence More Environmentally Sustainable

DevFeed: [How to Make Artificial Intelligence More Environmentally Sustainable](<https://devfeed.tech/articles/how-to-make-artificial-intelligence-more-environmentally-sustainable-106250.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/10/AI-environmentally-sustainable/>)

Author: Ben Linders

Published: 2026-10-29T11:41:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [clean energy data centers](<https://devfeed.tech/topics/clean-energy-data-centers.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-environmentally-sustainable](<https://devfeed.tech/tags/ai-environmentally-sustainable.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [cloud-computing](<https://devfeed.tech/tags/cloud-computing.md>), [compute](<https://devfeed.tech/tags/compute.md>), [culture-methods](<https://devfeed.tech/tags/culture-methods.md>), [data](<https://devfeed.tech/tags/data.md>), [development](<https://devfeed.tech/tags/development.md>), [electricity](<https://devfeed.tech/tags/electricity.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [energy](<https://devfeed.tech/tags/energy.md>), [goto-conference](<https://devfeed.tech/tags/goto-conference.md>), [green-software](<https://devfeed.tech/tags/green-software.md>), [it](<https://devfeed.tech/tags/it.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [models](<https://devfeed.tech/tags/models.md>), [news](<https://devfeed.tech/tags/news.md>), [renewable-energy](<https://devfeed.tech/tags/renewable-energy.md>), [sustainability](<https://devfeed.tech/tags/sustainability.md>), [sustainable-computing](<https://devfeed.tech/tags/sustainable-computing.md>), [train](<https://devfeed.tech/tags/train.md>)

### AI overview

The excerpt argues that AI's growing electricity demand makes sustainability a top-level architecture concern: reports cited show rising emissions at Microsoft and Google, while data centers and networks account for substantial electricity use. To reduce impact, assess whether AI is needed, reuse or fine-tune pre-trained models, choose smaller models, and optimize both training and production inference. Carbon-aware demand shifting can move latency-tolerant work to cleaner times or regions; demand shaping can reduce or change work as electricity gets dirtier, through options such as smaller models or lower-quality media. These approaches may add complexity and reduce service quality, so teams must judge whether the tradeoff is acceptable. The excerpt also recommends efficient hardware and execution, cloud providers with cleaner locations and useful footprint tools, and collecting data when and where renewable energy is available.

### Source excerpt

IT is responsible for about 2 - 4% of all global emissions, and electricity use at Microsoft and Google has climbed because of AI, according to their own reports. Sustainability ought to be a top-level architectural concern. Some recommendations are: use pre-built and smaller models, run compute where low-carbon electricity is abundant, and train on renewable energy. By Ben Linders

## Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting

DevFeed: [Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting](<https://devfeed.tech/articles/improving-the-energy-efficiency-of-the-code-generated-by-llms-through-effective-prompting-99841.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.02571>)

Author: Ritika Rekhi, Bing Zhang, Md Arman Islam, Jaya Krishna Pasham, Yeswanth Chitturi, Akshay Paramesha, Isha Valiveti, Asif Imran, Bekir Turkkan, Tevfik Kosar

Published: 2026-10-26T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Green Software](<https://devfeed.tech/topics/green-software.md>), [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [Code quality](<https://devfeed.tech/topics/code-quality.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted-programming](<https://devfeed.tech/tags/ai-assisted-programming.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [code](<https://devfeed.tech/tags/code.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [effective-prompting](<https://devfeed.tech/tags/effective-prompting.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [energy](<https://devfeed.tech/tags/energy.md>), [energy-efficiency](<https://devfeed.tech/tags/energy-efficiency.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [llms](<https://devfeed.tech/tags/llms.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [prompting](<https://devfeed.tech/tags/prompting.md>), [python](<https://devfeed.tech/tags/python.md>), [software](<https://devfeed.tech/tags/software.md>), [strategies](<https://devfeed.tech/tags/strategies.md>)

### AI overview

The study reports that prompting can reduce the energy use of LLM-generated code, though results vary by model and language. It evaluated eight selected strategies against a baseline across 10 open-weight and proprietary models, generating Python and C++ code. Across models, reductions reached 25% for Python and 17% for C++; reported model-specific peaks included 50% for Granite-4.0-H-Small in Python and 57% for the same model in C++. The abstract gives no details about individual prompting strategies or measurement methods.

### Source excerpt

arXiv:2610.02571v2 Announce Type: replace-cross Abstract: As AI-assisted programming becomes increasingly mainstream, the environmental impact of AI-generated software has emerged as an important consideration. This motivates evaluating LLM-generated code beyond functional correctness by considering execution efficiency and energy consumption. However, despite substantial advances in code generation, frontier LLMs are rarely evaluated based on the energy efficiency of the code they produce. In this work, we conduct a comprehensive evaluation of 21 prompting strategies for energy-efficient code generation and identify 8 strategies for evaluation across 10 widely used open-weight and proprietary LLMs. We evaluate their effectiveness for both Python and C++ code generation relative to a baseline prompt. Across the evaluated models, the selected prompting strategies achieved energy reductions of up to 25% for Python and 17% for C++ code generation. At the model level, Python energy reductions reached up to 50% for Granite-4.0-H-Small, 39% for Claude 4.5 Haiku, and 28% for MiniMax M3, while C++ reductions reached up to 57% for Granite-4.0-H-Small and 6.4% for Qwen3-Coder-480B-A35B-Instruct. These results demonstrate that prompting strategies can substantially influence the energy consumption of LLM-generated code, although their effectiveness varies across models and programming languages. Our findings highlight the importance of incorporating energy efficiency into the evaluation and optimization of LLM-based code generation and provide practical insights into designing prompts for more sustainable AI-assisted programming.

## Generalized green and red concepts for artificial intelligence, big data, and information and communication technologies: Multidimensional framework and countermeasures

DevFeed: [Generalized green and red concepts for artificial intelligence, big data, and information and communication technologies: Multidimensional framework and countermeasures](<https://devfeed.tech/articles/generalized-green-and-red-concepts-for-artificial-intelligence-big-data-and-information-and-communication-technologies-multidimensional-framework-and-countermeasures-99896.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.31739>)

Author: Jinsong Wu, Yixin Xiao, Haowei Bi, Huamin Fang

Published: 2026-10-26T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>), [clean energy data centers](<https://devfeed.tech/topics/clean-energy-data-centers.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [ai](<https://devfeed.tech/tags/ai.md>), [analyze](<https://devfeed.tech/tags/analyze.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [big-data](<https://devfeed.tech/tags/big-data.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [communication](<https://devfeed.tech/tags/communication.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [data-centers](<https://devfeed.tech/tags/data-centers.md>), [demand](<https://devfeed.tech/tags/demand.md>), [design](<https://devfeed.tech/tags/design.md>), [design-principles](<https://devfeed.tech/tags/design-principles.md>), [development](<https://devfeed.tech/tags/development.md>), [development-practices](<https://devfeed.tech/tags/development-practices.md>), [digital](<https://devfeed.tech/tags/digital.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [electrical-engineering](<https://devfeed.tech/tags/electrical-engineering.md>), [electricity](<https://devfeed.tech/tags/electricity.md>), [framework](<https://devfeed.tech/tags/framework.md>), [green](<https://devfeed.tech/tags/green.md>), [red](<https://devfeed.tech/tags/red.md>)

### AI overview

The paper proposes a unified E/Ec/S/T framework to assess sustainability impacts across AI, big data, and ICT, extending "green" and "red" concepts beyond energy and carbon to lifecycle trade-offs and electricity, water, materials, and e-waste. It describes how risks can propagate across technology stacks and service-use boundaries, then groups countermeasures into four tiers: reform footprint metrics for accountability; revise ICT design and shape demand; improve LLM data, model, training, and scaling practices for efficiency; and transition energy infrastructure. The abstract frames these measures as a way to prioritize interventions while preserving utility. It estimates data centers could use 6.7-12% of U.S. electricity by 2028, versus 4.4% in 2023, and AI-related water demand could reach 4-6 billion m³ annually by 2027.

### Source excerpt

arXiv:2610.31739v1 Announce Type: cross Abstract: The rapid expansions of artificial intelligence (AI), big data (BD), and information and communication technologies (ICT) are driving substantial growth in electricity, water, and material demands, with data centers projected to consume 6.7--12\% of U.S. electricity by 2028 (up from 4.4\% in 2023) and AI-related water demand estimated at 4--6 billion m$^3$ annually by 2027. Existing ``green AI'' and ``red AI'' discussions have largely emphasized computational efficiency and carbon emissions, providing limited guidance for lifecycle trade-offs, service-versus-use impacts, and broader sustainability externalities beyond energy. To bridge this gap, this paper proposes generalized green AI (GGAI) and generalized red AI (GRAI) and extends the taxonomy to red BD (RBD) and red ICT (RICT) as well as red electronic and electrical engineering (REEE) \& red digital technologies (RDT) under a unified Environmental-Economic-Social-Technical/Operational (E/Ec/S/T) framework. Based on representative footprint indicators in the large-model era (electricity, carbon, water, and e-waste), we analyze how risks propagate across AI-BD-ICT stacks and across service-use boundaries. We further organize actionable countermeasures into a four-tier taxonomy aligned with the Environmental-Economic-Social-Technical/Operational framework: metric-level reform for accountability, revision of information and communication technologies design principles and demand shaping, efficiency-oriented LLM development practices (data, model, training, and scaling), and energy-infrastructure transition. The proposed framework operationalizes the Environmental-Economic-Social-Technical/Operational-aligned assessment and intervention prioritization across the AI-BD-ICT stacks, enabling sustainability-by-design without sacrificing utility.

## Sustainability of TSFM Deployment and Pretraining: From Carbon Footprint Analysis to Mitigation via Pruning

DevFeed: [Sustainability of TSFM Deployment and Pretraining: From Carbon Footprint Analysis to Mitigation via Pruning](<https://devfeed.tech/articles/sustainability-of-tsfm-deployment-and-pretraining-from-carbon-footprint-analysis-to-mitigation-via-pruning-99667.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.32859>)

Author: C\\'ecile Luc, Nathana\\"el Lemonnier, Ievgen Redko

Published: 2026-10-26T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Post-training optimization](<https://devfeed.tech/topics/post-training-optimization.md>), [Time Series](<https://devfeed.tech/topics/time-series.md>), [Green Software](<https://devfeed.tech/topics/green-software.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [block](<https://devfeed.tech/tags/block.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [carbon-footprint](<https://devfeed.tech/tags/carbon-footprint.md>), [co2](<https://devfeed.tech/tags/co2.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [latency](<https://devfeed.tech/tags/latency.md>), [lifecycle](<https://devfeed.tech/tags/lifecycle.md>), [mitigation](<https://devfeed.tech/tags/mitigation.md>), [model](<https://devfeed.tech/tags/model.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pretraining](<https://devfeed.tech/tags/pretraining.md>), [reduction](<https://devfeed.tech/tags/reduction.md>), [series](<https://devfeed.tech/tags/series.md>), [sustainability](<https://devfeed.tech/tags/sustainability.md>)

### AI overview

The abstract finds that whether Chronos-2's pretraining emissions pay off depends on deployment scale and query frequency: in the modeled industrial scenario, those costs are amortized within months for large or frequently queried deployments, while a classical model remains cheaper indefinitely for small or infrequent ones. To reduce TSFM costs, a gradient-free criterion removes one encoder block (7.9% of parameters), cutting FLOPs, CO2 emissions, and latency by 6-9% with essentially no zero-shot forecasting performance loss across 25 benchmark tasks.

### Source excerpt

arXiv:2610.32859v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) offer strong zero-shot forecasting capabilities, but their high pretraining cost raises a practical sustainability question: does this upfront investment pay off over a full deployment lifecycle, compared to supervised standalone models that must be periodically retrained? We model the cumulative carbon cost of different approaches across a realistic industrial scenario: Chronos-2 amortizes its pretraining cost within months for large or frequently queried deployments, but a classical model remains cheaper indefinitely for small or rarely queried ones. For cases where reducing the TSFM's own cost matters, we show that removing a single encoder block (7.9% of parameters) via a gradient-free pruning criterion yields a consistent 6 to 9% reduction in FLOPs, CO2 emissions, and latency, at essentially no cost to zero-shot forecasting performance across a 25-task benchmark.

## Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations

DevFeed: [Green Code or Costly Code? Evaluating the Energy Costs of Iterative LLM-Based Code Optimizations](<https://devfeed.tech/articles/green-code-or-costly-code-evaluating-the-energy-costs-of-iterative-llm-based-code-optimizations-100059.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.32891>)

Author: Sadra Emami, Benjamin Weigell, Mohammad Reza Mousavi, Gunel Jahangirova, Hugo Araujo, Bernhard Bauer

Published: 2026-10-26T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Green Software](<https://devfeed.tech/topics/green-software.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Sustainable Computing](<https://devfeed.tech/topics/sustainable-computing.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [art](<https://devfeed.tech/tags/art.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [canonical](<https://devfeed.tech/tags/canonical.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [code](<https://devfeed.tech/tags/code.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [energy](<https://devfeed.tech/tags/energy.md>), [energy-costs](<https://devfeed.tech/tags/energy-costs.md>), [green](<https://devfeed.tech/tags/green.md>), [llm](<https://devfeed.tech/tags/llm.md>), [optimizations](<https://devfeed.tech/tags/optimizations.md>)

### AI overview

Across 1,000 EffiBench problems, 42 of 44 tested configurations of LLM self-refinement produced code that used more energy per problem than canonical human solutions, by 4% to 886%. The two energy-saving exceptions offered only marginal gains, with estimated break-even points after roughly one million to ten million executions. The study tested 11 open-source models across four decoding configurations and measured energy per process. Inference energy ranged from 0.79 to 8.68 MJ per model-variant pair; limiting maximum output tokens cut it by up to 69%. Mixture-of-Experts models used substantially less inference energy than similarly sized dense models without reduced correctness. The abstract concludes that faster-seeking optimization does not necessarily yield energy-efficient code; its findings are limited to the tested benchmark and configurations.

### Source excerpt

arXiv:2610.32891v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to optimize code for performance. This practice often assumes that improvements in execution speed naturally translate into overall lower energy consumption. We challenge this assumption empirically by measuring whether performance-optimized code produced by LLM self-refinement pipelines is also energy-efficient relative to canonical human reference solutions, and whether the energy cost of the optimization process can be offset by subsequent execution-time savings. We evaluate 11 open-source models across four decoding configurations on all 1,000 problems of EffiBench, a state-of-the-art performance benchmark, while collecting per-process, hardware-level energy measurements throughout. Inference energy spans 0.79 to 8.68 MJ across model-variant pairs, which is roughly equivalent to the energy of 250 to 2800 GPT-4.1 queries. Limiting the maximum number of output tokens has the largest impact, reducing energy use by up to 69% compared to the default configuration. On the execution side, 42 of 44 configurations produce code that consumes more energy per problem than the canonical human reference, with overheads ranging from +4% to +886%. The two exceptions achieve only marginal gains, with break-even points on the order of 10^6 to 10^7 executions. Mixture-of-Experts architectures consume substantially less inference energy than equivalently-sized dense models without sacrificing correctness, making architectural choice a more consequential sustainability lever than decoding parameters. Performance optimization and energy efficiency are not always aligned goals: LLM self-refinement consistently produces faster-seeking but energy-heavier code relative to what a human engineer would write. All artifacts are available at https://doi.org/10.5281/zenodo.23598170.

## The same AI question emits more carbon dioxide in Texas than in Sweden

DevFeed: [The same AI question emits more carbon dioxide in Texas than in Sweden](<https://devfeed.tech/articles/the-same-ai-question-emits-more-carbon-dioxide-in-texas-than-in-sweden-93908.md>)

Original publisher: [Read original article](<https://www.cio.com/article/4238689/the-same-ai-project-emits-more-carbon-dioxide-in-texas-than-in-sweden.html>)

Author: Viktor Eriksson

Published: 2026-10-21T20:42:49Z

Content type: news

Language: en

Sources: [CIO](<https://devfeed.tech/sources/cio.md>)

Topics: [Green Software](<https://devfeed.tech/topics/green-software.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [ai-requests](<https://devfeed.tech/tags/ai-requests.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-data-center-generative-ai-sustainable-it](<https://devfeed.tech/tags/artificial-intelligence-data-center-generative-ai-sustainable-it.md>), [calculator](<https://devfeed.tech/tags/calculator.md>), [carbon-dioxide](<https://devfeed.tech/tags/carbon-dioxide.md>), [climate](<https://devfeed.tech/tags/climate.md>), [compare](<https://devfeed.tech/tags/compare.md>), [data-center](<https://devfeed.tech/tags/data-center.md>), [edition-us](<https://devfeed.tech/tags/edition-us.md>), [emissions](<https://devfeed.tech/tags/emissions.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [germany](<https://devfeed.tech/tags/germany.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [impact](<https://devfeed.tech/tags/impact.md>), [ireland](<https://devfeed.tech/tags/ireland.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [regions](<https://devfeed.tech/tags/regions.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>), [sustainable-it](<https://devfeed.tech/tags/sustainable-it.md>), [sweden](<https://devfeed.tech/tags/sweden.md>), [texas](<https://devfeed.tech/tags/texas.md>), [web-based](<https://devfeed.tech/tags/web-based.md>)

### AI overview

Berget AI, the Stockholm Environment Institute, WattTime, and Klimatkollen developed a method to estimate emissions per AI request, aiming to help companies compare suppliers and make the industry's climate impact more transparent. For a typical request to Kimi K3, it estimates about 0.4 g of CO₂ in Sweden, 1.6 g in Ireland, 2.5 g in Germany, and 3.2 g in Texas, despite identical hardware. Berget AI released the method as open source, and a web calculator lets users compare estimates across AI models and regions.

### Source excerpt

The Swedish AI company Berget AI, together with researchers from the Stockholm Environment Institute (SEI) and the organizations WattTime and Klimatkollen, has developed a new method for calculating how much carbon dioxide different AI requests generate. The aim is to make the AI industry's climate impact more transparent and give companies the opportunity to compare different suppliers. According to the method, for example, a typical request to the AI model Kimi K3 results in around 0.4 grams of carbon dioxide emissions in Sweden, 1.6 grams in Ireland, 2.5 grams in Germany, and 3.2 grams in Texas. Despite identical hardware. Berget AI has published the method as open source, meaning other companies can freely use it. A web-based calculator also makes it possible to compare emissions between different AI models and geographical regions.

## Magneton: Optimizing Energy Efficiency of ML Systems via Differential Energy Debugging

DevFeed: [Magneton: Optimizing Energy Efficiency of ML Systems via Differential Energy Debugging](<https://devfeed.tech/articles/magneton-optimizing-energy-efficiency-of-ml-systems-via-differential-energy-debugging-93732.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2512.08365>)

Author: Yi Pan, Wenbo Qian, Dedong Xie, Ruiyan Hu, Yigong Hu, Baris Kasikci

Published: 2026-10-21T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Green Software](<https://devfeed.tech/topics/green-software.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>)

Tags: [applications](<https://devfeed.tech/tags/applications.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [developers](<https://devfeed.tech/tags/developers.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [energy](<https://devfeed.tech/tags/energy.md>), [energy-efficiency](<https://devfeed.tech/tags/energy-efficiency.md>), [frameworks](<https://devfeed.tech/tags/frameworks.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llm-inference](<https://devfeed.tech/tags/llm-inference.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [ml](<https://devfeed.tech/tags/ml.md>), [operator](<https://devfeed.tech/tags/operator.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [optimizing](<https://devfeed.tech/tags/optimizing.md>), [performance](<https://devfeed.tech/tags/performance.md>), [software](<https://devfeed.tech/tags/software.md>), [software-design](<https://devfeed.tech/tags/software-design.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

Magneton uses differential energy debugging to find software energy waste in machine learning systems. It compares similar systems' energy use at the operator level and pinpoints code regions and configuration choices linked to excess consumption. In evaluations across nine systems covering LLM inference, general ML frameworks, and image generation, it diagnosed 16 known inefficiencies and found eight previously unknown cases; developers confirmed seven of those discoveries.

### Source excerpt

arXiv:2512.08365v2 Announce Type: replace Abstract: The training and deployment of machine learning (ML) models have become extremely energy-intensive. While existing optimization efforts focus primarily on hardware energy efficiency, a significant but overlooked source of inefficiency is software energy waste caused by poor software design. This often includes redundant or poorly designed operations that consume more energy without improving performance. These inefficiencies arise in widely used ML frameworks and applications, yet developers often lack the visibility and tools to detect and diagnose them. We propose differential energy debugging, a novel approach that leverages the observation that competing ML systems often implement similar functionality with vastly different energy consumption. Building on this insight, we design and implement Magneton, an energy profiler that compares energy consumption between similar ML systems at the operator level and automatically pinpoints code regions and configuration choices responsible for excessive energy use. Applied to 9 popular ML systems spanning LLM inference, general ML frameworks, and image generation, Magneton detects and diagnoses 16 known cases of software energy inefficiency and further discovers 8 previously unknown cases, 7 of which have been confirmed by developers.

[Next page](<https://devfeed.tech/topics/green-software.md?cursor=WyIyMDI2LTEwLTIxVDA0OjAwOjAwKzAwOjAwIiwgIjFmZTIxNDhmLWY2YzctNGY0YS1iZDdhLWFkNGNiYjVhMTY3MSJd>)