| 注册
首页|期刊导航|电测与仪表|基于CEQ(λ)强化学习算法的微电网智能发电控制

基于CEQ(λ)强化学习算法的微电网智能发电控制

唐捷 张泽宇 程乐峰 张孝顺 余涛

电测与仪表2017,Vol.54Issue(1):39-45,7.
电测与仪表2017,Vol.54Issue(1):39-45,7.

基于CEQ(λ)强化学习算法的微电网智能发电控制

Smart generation control for micro-grids based on correlated equilibrium Q(λ) learning algorithm

唐捷 1张泽宇 2程乐峰 2张孝顺 2余涛2

作者信息

  • 1. 广东电网有限责任公司韶关供电局,广东韶关512026
  • 2. 华南理工大学电力学院,广州510640
  • 折叠

摘要

Abstract

In view of addressing frequency fluctuation problem of the islanded micro-grid caused by strong randomness of renewable energy , this paper proposes a smart generation control method of micro-grid based on multi-agent correla-ted equilibrium Q(λ).After establishing the micro-grid load frequency control (LFC) model containing photovoltaic generation , wind generation , small hydro unit , micro-gas turbine and flywheel energy storage , which takes frequency deviation as the input , a smart generation controller based on correlated equilibrium Q (λ) has been proposed .Simu-lation analysis , compared with PI controller , R (λ) learning controller , shows that correlated equilibrium controller has better online learning ability , and enhances robustness and adaptability of islanded micro-grid remarkably and im-proves the pass rate of frequency assessment effectively .

关键词

多智能体/相关均衡/强化学习/微电网/智能发电控制

Key words

multi-agent/correlated equilibrium/reinforcement learning/micro-grid/smart generation control

分类

信息技术与安全科学

引用本文复制引用

唐捷,张泽宇,程乐峰,张孝顺,余涛..基于CEQ(λ)强化学习算法的微电网智能发电控制[J].电测与仪表,2017,54(1):39-45,7.

基金项目

国家自然科学基金资助项目(51177051) (51177051)

中国南方电网科技项目资助(02DKHK1200059) (02DKHK1200059)

电测与仪表

OA北大核心

1001-1390

访问量0
|
下载量0
段落导航相关论文