Federated Learning With Energy Harvesting Devices: An MDP Framework
This addresses the practical challenge of battery depletion in edge devices for federated learning, which impacts operational lifespan and learning performance, though it appears incremental by applying existing MDP and reinforcement learning methods to this specific domain.
The paper tackles the problem of energy consumption in federated learning systems by implementing energy harvesting techniques to power edge devices, establishing convergence bounds affected by energy supply, and developing optimal transmission policies and low-complexity algorithms that accelerate convergence, with numerical experiments validating these results.
Federated learning (FL) necessitates that edge devices conduct local training and communicate with a parameter server, resulting in significant energy consumption. A key challenge in practical FL systems is the rapid depletion of battery-limited edge devices, which limits their operational lifespan and impacts learning performance. To tackle this issue, we implement energy harvesting techniques in FL systems to capture ambient energy, thereby providing continuous power to edge devices. We first establish the convergence bound for the wireless FL system with energy harvesting devices, illustrating that the convergence is affected by partial device participation and packet drops, both of which depend on the energy supply. To accelerate the convergence, we formulate a joint device scheduling and power control problem and model it as a Markov decision process (MDP). By solving this MDP, we derive the optimal transmission policy and demonstrate that it possesses a monotone structure with respect to the battery and channel states. To overcome the curse of dimensionality caused by the exponential complexity of computing the optimal policy, we propose a low-complexity algorithm, which is asymptotically optimal as the number of devices increases. Furthermore, for unknown channels and harvested energy statistics, we develop a structure-enhanced deep reinforcement learning algorithm that leverages the monotone structure of the optimal policy to improve the training performance. Finally, extensive numerical experiments on real-world datasets are presented to validate the theoretical results and corroborate the effectiveness of the proposed algorithms.