The invention discloses an electric vehicle (EV) battery charging regulation and control method based on multi-agent reinforcement learning (RL), and the method mainly utilizes Markov decision process modeling and unsupervised learning (RL) to optimize the electric power supply of EV battery charging, so as to cut and fill the peak-valley difference caused by large-scale access of EV battery load, and facilitate the benefit maximization of a supply side and an EV user. The method does not depend on excessive EV battery charging regulation and control priori knowledge and accurate modeling, the optimal regulation and control strategy is obtained through online heuristic learning, and the energy supply accuracy and the effective utilization rate can be improved.
本发明公开了一种基于多智能体强化学习(Reinforcement Learning,RL)的电动汽车(Electric Vehicle,EV)电池充电调控方法,主要利用马尔可夫决策过程建模与非监督学习RL来优化EV电池充电的电力供给,用以削填EV电池负荷大规模接入引起的峰谷差,并有助于供给侧与EV用户的利益最大化。本发明不依赖过多的EV电池充电调控先验知识和精确建模,通过在线启发式学习获得最优调控策略,有利于提高能源供给精准度和有效利用率。
Electric vehicle battery charging regulation and control method based on multi-agent reinforcement learning
一种基于多智能体强化学习的电动汽车电池充电调控方法
2022-03-11
Patent
Elektronische Ressource
Chinesisch
IPC: | G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES |
Reinforcement Learning Based Fast Charging of Electric Vehicle Battery Packs
SAE Technical Papers | 2023
|Europäisches Patentamt | 2023
|REINFORCEMENT LEARNING-BASED ELECTRIC VEHICLE CHARGING METHOD AND SYSTEM
Europäisches Patentamt | 2021
|Europäisches Patentamt | 2023
|Europäisches Patentamt | 2023
|