Over-the-Air Federated Learning with Energy Harvesting Devices

We consider federated edge learning among mobile devices that harvest the required energy from their surroundings, and share their updates with the parameter server (PS) through a shared wireless channel. In particular, we consider energy harvesting FL with over-the-air (OTA) aggregation, where the participating devices perform local computations and wireless transmission only when they have the required energy available, and transmit the local updates simultaneously over the same channel bandwidth. In order to prevent bias among the heterogeneous devices, we utilize a weighted averaging with respect to their latest energy arrivals and data cardinalities. We provide a convergence analysis and carry out numerical experiments with different energy arrival profiles, which show that the proposed scheme is robust against heterogeneous energy arrivals in error-free scenarios while having less than 10% performance loss for fading channels.