Deep Reinforcement Learning Based Coordinated Voltage Control in Smart Distribution Network
Authors:
- 8 December 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1030-1034
Abstract
This paper designs a reactive power optimization strategy based on multi-agent deep reinforcement learning soft actor-critic (MASAC) algorithm. Compared with the traditional method, our proposed method does not depend on accurate power flow modeling based on the data prediction of day-ahead load and distributed generation data. The proposed strategy uses deep neural network to train the action functions of solar photovoltaic (PV) and wind turbine (WT) inverters as multiple agents and completes the training of deep neural networks in the process of interaction with the distribution network environment. Additionally, centralized training and decentralized execution framework are adopted to solve the Volt-VAR control problem. In our MASAC algorithm, each agent is regarded as an actor trained with a critic during the training process. Finally, a numerical study is given to verify the effectiveness of the MASAC algorithm.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 16 references indexed in Scilit:
- Coordinated Control Method of Voltage and Reactive Power for Active Distribution Networks Based on Soft Open PointIEEE Transactions on Sustainable Energy, 2017
- Real-Time Co-Simulation Platform for Smart Grid Volt-VAR Optimization Using IEC 61850IEEE Transactions on Industrial Informatics, 2016
- Optimal sizing of autonomous hybrid photovoltaic/wind/battery power system with LPSP technology by using evolutionary algorithmsSolar Energy, 2015
- Promises of Conic Relaxation for Contingency-Constrained Optimal Power Flow ProblemIEEE Transactions on Power Systems, 2015
- Distributed Volt/VAr Control by PV InvertersIEEE Transactions on Power Systems, 2013
- Smart inverter volt/var control functions for high penetration of PV on distribution systems2011
- Reactive Power and Voltage Control in Distribution Systems With Limited Switching OperationsIEEE Transactions on Power Systems, 2009
- An improved TS algorithm for loss-minimum reconfiguration in large-scale distribution systemsElectric Power Systems Research, 2007
- Mixed Integer Linear Programming in Process Scheduling: Modeling, Algorithms, and ApplicationsAnnals of Operations Research, 2005
- Reinforcement Learning for Reactive Power ControlIEEE Transactions on Power Systems, 2004