As the number of electric vehicles (EVs) increases, reinforcement learning (RL) in EV charging scheduling faces challenges, particularly uncertainties and the curse of dimensionality from large‑scale applications. A microgrid model for residential areas, considering the vehicle‑to‑grid (V2G) mode and various nonlinear charging models is developed. The problem is formulated as a constrained Markov decision process (CMDP), with a model‑free RL framework to handle uncertainties. To address the curse of dimensionality, a strategy is designed where EVs are grouped by states, and agents send control signals to these sets, thus reducing the dimensionality of the action space. A Lagrangian deep deterministic policy gradient (LDDPG) algorithm is employed to solve the charging scheduling problem, with a safety filter ensuring constraint compliance. Numerical simulations validate the strategy’s effectiveness.
ZhengY C, NiuS Y, ShangY T,et al.Integrating plug‑in electric vehicles into power grids:a comprehensive review on power interaction mode,scheduling methodology and mathematical foundation[J].Renewable & Sustainable Energy Reviews,2019,112:424-439.
[2]
WangB, ZhaoD B, DehghanianP,et al.Aggregated electric vehicle load modeling in large‑scale electric power systems[J].IEEE Transactions on Industry Applications,2020,56(5):5796-5810.
[3]
KemptonW, LetendreS E.Electric vehicles as a new power source for electric utilities[J].Transportation Research Part D:Transport and Environment,1997,2(3):157-175.
[4]
IslamS, IqbalA, MarzbandM,et al.State‑of‑the‑art vehicle‑to‑everything mode of operation of electric vehicles and its future perspectives[J].Renewable and Sustainable Energy Reviews,2022,166:112574.
[5]
ZhouC Q, XiangY, HuangY,et al.Economic analysis of auxiliary service by V2G:city comparison cases[J].Energy Reports,2020,6:509-514.
WangQ L, LiuX, DuJ,et al.Smart charging for electric vehicles:a survey from the algorithmic perspective[J].IEEE Communications Surveys & Tutorials,2016,18(2):1500-1517.
[8]
LuoC, HuangY F, GuptaV.Stochastic dynamic pricing for EV charging stations with renewable integration and energy storage[J].IEEE Transactions on Smart Grid,2018,9(2):1494-1505.
[9]
KalashnikovD, VarleyJ, ChebotarY,et al.Scaling up multi‑task robotic reinforcement learning[C]//Proceedings of the 5th Conference on Robot Learning.London,2022:557-575.
[10]
HuangQ L, YangL, HouC,et al.Event-based EV charging scheduling in a microgrid of buildings[J].IEEE Transactions on Transportation Electrification,2023,9(1):1784-1796.
[11]
WangY Q, ZhangJ, LiL,et al.Research on coordinated charging control strategy load optimization of electric vehicles in residential area[J].IOP Conference Series:Earth and Environmental Science,2020,510(6):062030.
[12]
ZhangT Y, PotaH, ChuC C,et al.Real-time renewable energy incentive system for electric vehicles using prioritization and cryptocurrency[J].Applied Energy,2018,226:582-594.
[13]
FanP Y, SainbayarB, RenS L.Operation analysis of fast charging stations with energy demand control of electric vehicles[J].IEEE Transactions on Smart Grid,2015,6(4):1819-1926.
SunHan‑mo, ShenZhu, GuoZong‑jun,et al.Research on the influence of different weather types on the theoretical power generation of photovoltaic power plants[J].Solar Energy,2017(6):38-42.