Deep reinforcement learning-based grid mind and field demonstration application

徐春雷; 吴海伟; 刁瑞盛; 胡浔惠; 李 雷; 史 迪

doi:10.3969/j.issn.1009-1831.2021.04.014

您当前的位置：

首页 >

文章列表页 >

Deep reinforcement learning-based grid mind and field demonstration application

更新时间：2026-03-05

- Deep reinforcement learning-based grid mind and field demonstration application
- Vol. 23, Issue 4, (2021)
- 作者机构：
  
  1. 国网江苏省电力有限公司,南京,210024
  2. 智博能源科技（江苏）有限公司,南京,211302
  3. 国电南瑞科技股份有限公司,南京,211106
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1009-1831.2021.04.014
  CLC：
- Published：2021
- 稿件说明：
移动端阅览
徐春雷, 吴海伟, 刁瑞盛, et al. Deep reinforcement learning-based grid mind and field demonstration application[J]. 2021, 23(4).
DOI：

徐春雷, 吴海伟, 刁瑞盛, et al. Deep reinforcement learning-based grid mind and field demonstration application[J]. 2021, 23(4). DOI： 10.3969/j.issn.1009-1831.2021.04.014.

摘要

可再生能源、电力电子设备渗透率持续增大以及大功率交直流混联，电网的动态性、随机性和不确定性显著增强，给电力系统安全稳定运行带来新的挑战。为更有效解决电网中出现的电压、潮流快速波动而导致的安全问题，提出一种基于最大熵深度强化学习算法的智能电网调控辅助决策方法，同时考虑多种控制目标，对电网运行方式进行在线优化控制。该方法将电网调度控制决策建模为马尔科夫决策过程，训练多线程智能体，并采用周期性在线训练机制对智能体的控制性能进行不断提升。基于该方法所研发的辅助决策原型软件部署在国网江苏电力调度控制中心，可与电网调度控制系统环境直接交互，自主学习且不断提升智能体调控决策能力。训练好的智能体可针对电压越限、联络线潮流越限、网损等综合控制目标在毫秒级时间内给出有效控制策略。

Abstract

With the increasing penetration of renewable energy and power electronics-based devices

and the hybrid operation of AC/DC power networks with heavy power transfer

the dynamics

stochastics and uncertainties of the power grid are being observed

threatening its secure operation. In order to effectively resolve security issues caused by fast variations of voltage and line flows

a reinforcement learning algorithm based on maximum entropy depth ispresented for providing online decision support in smart grid operation

which can simultaneously consider multiple control objectives.This method formulates decision derivation for grid operation as Markov decision process

which trains multi-threaded soft actor-critic and uses periodic online training mechanism to continuously improve its control performance. The developed prototype using this method has been deployed in the control center of SGCC Jiangsu electric power company

which interacts with live energy management system and learns its control policy adaptively. The well -trained agent can provide effective control actions within milliseconds to regulate voltage violation

line flow and losses.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Optimization scheduling of photovoltaic-hydrogen-storage for new energy vehicle charging station based on deep reinforcement learning

A PID-Lagrange-SAC based deep reinforcement learning strategy for building energy management

Low-carbon economic scheduling of virtual power plant based on proximal policy optimization

Collaborative control strategy for household air conditioners with adaptive access

Research on energy optimization allocation strategy for microgrids based on double delay deep deterministic strategy gradient algorithm

Related Author

聂兴鹏

张帅

李学军

苏勋文

赵为光

刘启航

杨莹

陈涛

Related Institution

黑龙江科技大学电气与控制工程学院

中国能源建设集团有限公司湖南省电力设计院

东南大学软件学院

东南大学电气工程学院

国网安徽省电力有限公司经济技术研究院

AI问答

⁰