论文标题
部分可观测时空混沌系统的无模型预测
Federated Reinforcement Learning for Real-Time Electric Vehicle Charging and Discharging Control
论文作者
论文摘要
随着移动储能技术的最新进展，电动汽车（EV）已成为智能电网的关键部分。当电动汽车参与需求响应计划时，通过充分利用实时定价信号可以大大降低充电成本。但是，在动态环境中存在许多随机因素，为设计最佳的充电/放电控制策略带来了重大挑战。本文在动态环境下为不同的EV用户开发了最佳的EV充电/放电控制策略，以最大程度地提高EV用户的好处。我们首先将此问题作为马尔可夫决策过程（MDP）。然后，我们将具有不同行为的电动汽车用户视为不同环境中的代理。此外，提出了一种基于水平的联合加固学习（HFRL）的方法，以适合各种用户的行为和动态环境。这种方法可以学习最佳的充电/放电控制策略，而无需共享用户的配置文件。仿真结果表明，提出的实时EV充电/放电控制策略可以在各种随机因素之间表现良好。
With the recent advances in mobile energy storage technologies, electric vehicles (EVs) have become a crucial part of smart grids. When EVs participate in the demand response program, the charging cost can be significantly reduced by taking full advantage of the real-time pricing signals. However, many stochastic factors exist in the dynamic environment, bringing significant challenges to design an optimal charging/discharging control strategy. This paper develops an optimal EV charging/discharging control strategy for different EV users under dynamic environments to maximize EV users' benefits. We first formulate this problem as a Markov decision process (MDP). Then we consider EV users with different behaviors as agents in different environments. Furthermore, a horizontal federated reinforcement learning (HFRL)-based method is proposed to fit various users' behaviors and dynamic environments. This approach can learn an optimal charging/discharging control strategy without sharing users' profiles. Simulation results illustrate that the proposed real-time EV charging/discharging control strategy can perform well among various stochastic factors.
