A Customized Voltage Control Strategy for Electric Vehicles in Distribution Networks With Reinforcement Learning Method
Authors:
- 8 January 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 17 (10) , 6852-6863
Abstract
The increasing electric vehicles (EVs) at charging stations will impose great challenges on the conventional voltage control in distribution networks. In this article, a two-stage voltage control strategy based on deep reinforcement learning is proposed to mitigate voltage violations caused by the uncertainty of EVs and load. In the first stage, the charging demand of EVs is predicted based on trip chain theory and simulated by Monte Carlo simulation. The optimal power flow is then performed to determine the day-ahead dispatch of on-load tap changer and capacitor banks. In the second stage, the real-time voltage control problem is formulated as a Markov Game considering both reactive power control and vehicle to grid modes of EVs. The problem is solved by the deep deterministic policy gradient algorithm to develop a well-trained control strategy that can be implemented online. Moreover, a novel customized charging criterion is proposed to conduct the charging behavior of EVs and guarantee full charging at the departure time. The proposed approach is tested on the IEEE 33-bus and 123-bus distribution systems and comparative simulation results show the effectiveness in addressing voltage problems.Keywords
Funding Information
- ARC Research Hub (IH180100020)
- ARC Training Centre (IC200100023)
- Sir William Tyree Foundation-Distributed Power Generation Research Fund
- National Natural Science Foundation of China (91746118)
- Shenzhen Municipal Science and Technology Innovation Committee (ZDSYS20170725140921348, JCYJ20170410172224515, JCYJ20160510153103492)
- NARI Technology Research Grant
- Comprehensive Energy System Simulation and Assessment Key Technology Research
This publication has 32 references indexed in Scilit:
- Charging demand for electric vehicle based on stochastic analysis of trip chainIET Generation, Transmission & Distribution, 2016
- A double-layer smart charging strategy of electric vehicles taking routing and charge scheduling into accountApplied Energy, 2016
- Mitigating Voltage Problem in Distribution System With Distributed Solar Generation Using Electric VehiclesIEEE Transactions on Sustainable Energy, 2015
- EV fast charging stations and energy storage technologies: A real implementation in the smart micro grid paradigmElectric Power Systems Research, 2015
- Human-level control through deep reinforcement learningNature, 2015
- Inverter-Less Hybrid Voltage/Var Control for Distribution Circuits With Photovoltaic GeneratorsIEEE Transactions on Smart Grid, 2014
- Convex Relaxation of Optimal Power Flow—Part II: ExactnessIEEE Transactions on Control of Network Systems, 2014
- Combined central and local control of reactive power in electrical grids with distributed generation2012
- Real-Time Coordination of Plug-In Electric Vehicle Charging in Smart Grids to Minimize Power Losses and Improve Voltage ProfileIEEE Transactions on Smart Grid, 2011
- Assessment of the Impact of Plug-in Electric Vehicles on Distribution NetworksIEEE Transactions on Power Systems, 2010