# Federated learning for remote IoT over LPWAN: Preliminary insights from structural health monitoring

DevFeed: [Federated learning for remote IoT over LPWAN: Preliminary insights from structural health monitoring](<https://devfeed.tech/articles/federated-learning-for-remote-iot-over-lpwan-preliminary-insights-from-structural-health-monitoring-126793.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11156>)

Author: Lakshmiprasanna Bandaru, Anshika Singh, Tarutal Ghosh Mondal, T. Jothi Saravanan, Siddhartha S. Borkotoky

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

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Internet of things](<https://devfeed.tech/topics/iot.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [health-monitoring](<https://devfeed.tech/tags/health-monitoring.md>), [iot](<https://devfeed.tech/tags/iot.md>), [latency](<https://devfeed.tech/tags/latency.md>), [lora](<https://devfeed.tech/tags/lora.md>), [lpwan](<https://devfeed.tech/tags/lpwan.md>)

## AI overview

The study investigates federated structural health monitoring over LoRa LPWAN, where limited data rates make model-update communication a constraint. Using SCAFFOLD for multi-class anomaly detection, it analyzes the latency-accuracy trade-off and ways to allocate LoRa spreading factors during updates. Numerical results indicate that selecting spreading factors jointly based on link distances and client dataset sizes can balance convergence performance and communication latency while retaining competitive accuracy. These are preliminary findings; the supplied text does not provide detailed numerical results.

## Source excerpt

arXiv:2611.11156v1 Announce Type: new Abstract: Realizing federated learning (FL) in remote regions lacking reliable cellular infrastructure is challenging, as it requires dependable communication among participating devices. Low-power wide-area networks (LPWANs) offer an attractive communication solution for such scenarios. However, their limited data rates necessitate careful investigation of the communication-learning trade-offs and mechanisms to reduce communication overhead. This paper presents an investigation of the Long Range (LoRa) LPWAN technology for FL-based structural health monitoring (SHM), a representative remote IoT application. We consider a SCAFFOLD-based FL framework for multi-class anomaly detection and analyze the latency-accuracy trade-off. We also examine strategies for allocating the LoRa spreading factor (SF) during model-update exchange. Numerical results show that, with appropriate SF allocation, LoRa-supported FL-SHM can achieve competitive learning accuracy. In particular, jointly accounting for link distances and clients' dataset sizes when selecting the SF provides a favorable balance between convergence performance and communication latency. These preliminary findings offer useful insights into the design of FL systems over LPWANs for remote IoT deployments.