A Multi-Agent Deep Reinforcement Learning Based Voltage Regulation Using Coordinated PV Inverters

被引：157

作者：

Cao, Di ^{[1
]}

Hu, Weihao ^{[1
]}

Zhao, Junbo ^{[2
]}

Huang, Qi ^{[1
]}

Chen, Zhe ^{[3
]}

Blaabjerg, Frede ^{[3
]}

机构：

[1] Univ Elect Sci & Technol China, Sch Mech & Elect Engn, Chengdu 610054, Peoples R China

[2] Mississippi State Univ, Dept Elect & Comp Engn, Starkville, MS 39762 USA

[3] Aalborg Univ, Dept Energy Technol, DK-9220 Aalborg, Denmark

来源：

IEEE TRANSACTIONS ON POWER SYSTEMS | 2020年 / 35卷 / 05期

关键词：

Voltage control; Training; Inverters; Markov processes; Games; Artificial neural networks; Real-time systems; Voltage regulation; multi-agent deep reinforcem-ent learning; coordinated control; distribution system; CONTROL STRATEGIES; NETWORK;

D O I：

10.1109/TPWRS.2020.3000652

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

080906 [电磁信息功能材料与结构]; 082806 [农业信息与电气工程];

摘要：

This paper proposes a multi-agent deep reinforcement learning-based approach for distribution system voltage regulation with high penetration of photovoltaics (PVs). The designed agents can learn the coordinated control strategies from historical data through the counter-training of local policy networks and centric critic networks. The learned strategies allow us to perform online coordinated control. Comparative results with other methods show the enhanced control capability of the proposed method under various conditions.

引用

页码：4120 / 4123

页数：4

共 12 条

[1]

Network-Cognizant Voltage Droop Control for Distribution Grids [J].