Byzantine-resilient Economical Operation Strategy Based on Federated Deep Reinforcement Learning for Multiple Electric Vehicle Charging Stations Considering Data Privacy  

作　　者：Bin Feng Huating Xu Gang Huang Zhuping Liu Chuangxin Guo Zhe Chen 

机构地区：[1]College of Electrical Engineering,Zhejiang University,Hangzhou 310027,China [2]Aalborg University,Aalborg 9220,Denmark

出　　处：《Journal of Modern Power Systems and Clean Energy》2024年第6期1957-1967,共11页现代电力系统与清洁能源学报(英文)

基　　金：This work was supported by the National Natural Science Foundation of China(No.52007173);the Joint Funds of National Natural Science Foundation of China(No.U22B2098);the National Key Research and Development Program of China(No.2023YFB3107603).

摘　　要：With the goal of low-carbon energy utilization,elec-tric vehicles(EVs)and EV charging stations(EVCSs)are be-coming increasingly popular.The economical operation strategy is always a primary concern for EVCSs,while users'behavior and operating data leakage problems in EVCSs have not been taken seriously.Herein,federated deep reinforcement learning,a privacy-preserving method,is applied to learn the optimal strategy for multiple EvCSs.However,it is prone to Byzantine attacks.It is urgent to achieve an economical operation strategy while preserving data privacy and defending against Byzantine attacks.Therefore,this paper proposes a Byzantine-resilient fed-erated deep reinforcement learning(BR-FDRL)method to ad-dress these problems.First,the distributed EVCS data are uti-lized by the federated deep reinforcement learning to train an economical operation strategy while preserving privacy by only transmitting gradients.The sampling efficiency is enhanced by both federated learning and stochastically controlled stochastic gradient.Then,the Byzantine-resilient gradient filter(BRGF)designs two distance rules to keep malicious gradients out.The case study verifies the effectiveness of the proposed BRGF in re-sisting Byzantine attacks and the effectiveness of federated deep reinforcement learning in improving convergence speed and re-ward and preserving privacy.The resluts show that the BR-FDRL method minimizes the operation cost by an average of 35%compared with the rule-based method while meeting the state of charge demand as much as possible.

关 键 词：Byzantine resilience federated learning deep reinforcement learning electric vehicle PRIVACY-PRESERVING economical operation 

分 类 号：P20[天文地球—测绘科学与技术]