Privacy Protection in Prosumer Energy Management Based on Federated Learning

TL;DR

This work tackles privacy-preserving prosumer energy management under Non-IID data by introducing FedClusAvg, a cluster-based extension of FedAvg that refines client data through stratified sampling and weights updates by parameter deviation, enabling multiple local iterations within a three-layer framework to reduce communication. It further extends the approach with FedClusAvg+, a multi-server deployment to improve scalability. Empirical evaluation on a cardiovascular dataset shows FedClusAvg achieving higher accuracy, precision, recall, F-measure, and KS than FedAvg, while FedClusAvg+ offers additional gains and stability. The results demonstrate practical potential for privacy-preserving, collaborative energy management in non-IID settings, with implications for scalable, distributed optimization in prosumer networks.

Abstract

With the booming development of prosumers, there is an urgent need for a prosumer energy management system to take full advantage of the flexibility of prosumers and take into account the interests of other parties. However, building such a system will undoubtedly reveal users' privacy. In this paper, by solving the non-independent and identical distribution of data (Non-IID) problem in federated learning with federated cluster average(FedClusAvg) algorithm, prosumers' information can efficiently participate in the intelligent decision making of the system without revealing privacy. In the proposed FedClusAvg algorithm, each client performs cluster stratified sampling and multiple iterations. Then, the average weight of the parameters of the sub-server is determined according to the degree of deviation of the parameter from the average parameter. Finally, the sub-server multiple local iterations and updates, and then upload to the main server. The advantages of FedClusAvg algorithm are the following two parts. First, the accuracy of the model in the case of Non-IID is improved through the method of clustering and parameter weighted average. Second, local multiple iterations and three-tier framework can effectively reduce communication rounds.

Figures (8)

• Figure 1: FedClusAvg algorithm
• Figure 2: FedClusAvg algorithm
• Figure 3: FedClusAvg+ algorithm
• Figure 4: the accuracy of FedClusAvg and FedAvg
• Figure 5: The value of KS of FedClusAvg and FedAvg via the (Top) FedClusAvg algorithm and (Button) FedAvg algorithm