Sliding Differential Evolution Scheduling for Federated Learning in Bandwidth-Limited Networks
This work addresses energy and bandwidth constraints in federated learning for networks with limited user equipment, but it is incremental as it builds on existing scheduling policies.
The paper tackles the problem of federated learning in bandwidth-limited networks with energy-constrained devices by proposing a sliding differential evolution-based scheduling policy, which reduces energy consumption and accelerates model convergence compared to existing methods.
Federated learning (FL) in a bandwidth-limited network with energy-limited user equipments (UEs) is under-explored. In this paper, to jointly save energy consumed by the battery-limited UEs and accelerate the convergence of the global model in FL for the bandwidth-limited network, we propose the sliding differential evolution-based scheduling (SDES) policy. To this end, we first formulate an optimization that aims to minimize a weighted sum of energy consumption and model training convergence. Then, we apply the SDES with parallel differential evolution (DE) operations in several small-scale windows, to address the above proposed problem effectively. Compared with existing scheduling policies, the proposed SDES performs well in reducing energy consumption and the model convergence with lower computational complexity.