Federated Aggregation via Artificial Bee Colony and Optimal Transport for Distributed Energy Systems

Abstract

The rapid development of multi-entity distributed energy systems has underscored the importance of source–grid–load–storage coordinated scheduling in improving renewable energy utilization and reducing operating costs. However, traditional centralized scheduling faces privacy risks, computational bottlenecks, and high latency, making it unsuitable for real-time distributed energy management. To address these challenges, this paper proposes a three-tier “device–edge–cloud” federated edge collaborative scheduling framework FedAOT, integrating an improved Artificial Bee Colony (ABC) algorithm with Optimal Transport (OT) for adaptive aggregation optimization. Specifically, an enhanced ABC is proposed to optimize the aggregation weight vector each round, while OT theory constructs optimal mapping relationships among client models, minimizing parameter distribution discrepancies. Simulation results demonstrate that the proposed method dynamically adapts to variations in data distribution and model quality, significantly improving global model accuracy and convergence speed.