On-Device Federated Learning for Remote Alpine Livestock Monitoring

Abstract

Alpine livestock monitoring is critical for ecological preservation and agricultural efficiency. However, existing solutions struggle with energy constraints, limited network availability, and intermittent connectivity in remote environments. To address this, we propose an on-device federated learning framework tailored for PV-powered IoT sensors to optimize energy-communication tradeoffs. Our approach introduces staleness-aware aggregation and solar-aware training scheduling to address intermittent connectivity and PV variability in remote alpine environments. Deployed on a real-world testbed with collar sensors, the framework achieves 92% accuracy in time-series location prediction and 89% F1-score in anomaly detection while using 68% less energy than centralized baselines.