Adaptive Load Frequency Control of Wind Power System Based on Online Reinforcement Learning

Li YANG; Yuanzhang SUN; Jian XU; Siyang LIAO; Liuyang PENG

doi:10.7500/AEPS20190706006

您当前的位置：

首页 >

文章列表页 >

Adaptive Load Frequency Control of Wind Power System Based on Online Reinforcement Learning

Basic Research | 更新时间：2025-06-16

- Adaptive Load Frequency Control of Wind Power System Based on Online Reinforcement Learning
- Automation of Electric Power Systems Vol. 44, Issue 12, Pages: 74-83(2020)
- 作者机构：
  
  武汉大学电气与自动化学院，湖北省武汉市 430072
- 作者简介：
- 基金信息：
  
  National Key R&D Program of China
- DOI：10.7500/AEPS20190706006
  CLC：
- Received：06 July 2019，
  
  Revised：2019-09-24，
  
  Published Online：30 April 2020，
  
  Published：25 June 2020
- 稿件说明：
移动端阅览
杨丽,孙元章,徐箭等.基于在线强化学习的风电系统自适应负荷频率控制[J].电力系统自动化,2020,44(12):74-83.

YANG Li,SUN Yuanzhang,XU Jian,et al.Adaptive Load Frequency Control of Wind Power System Based on Online Reinforcement Learning[J].Automation of Electric Power Systems,2020,44(12):74-83.
杨丽,孙元章,徐箭等.基于在线强化学习的风电系统自适应负荷频率控制[J].电力系统自动化,2020,44(12):74-83. DOI： 10.7500/AEPS20190706006.

YANG Li,SUN Yuanzhang,XU Jian,et al.Adaptive Load Frequency Control of Wind Power System Based on Online Reinforcement Learning[J].Automation of Electric Power Systems,2020,44(12):74-83. DOI： 10.7500/AEPS20190706006.

摘要

大规模风电接入给系统带来新的不确定性，影响系统频率响应特性，从数据驱动的角度出发，提出了一种基于自适应动态模型的在线强化学习方法，用于系统的负荷频率控制。建立低秩自编码器特征提取网络，从所量测的低维数据中发现隐藏特征；基于特征网络，建立非线性动态系统稀疏辨识学习模型，感知系统动态模型的潜在物理状态，提升模型在线学习效率；通过结合模型预测控制，进行实时决策控制。所提出方法能够有效解决传统模型预测控制对系统全局模型准确性的依赖问题，加强控制器对系统动态模型的自适应性，且能有效跟踪风电输出功率的随机波动。最后，以接入四型风机的负荷频率控制模型为例，验证所提方法的有效性。

Abstract

Large-scale wind power connected to the gird brings new uncertainties which affects the frequency response characteristics of the system. From the data-driven perspective

an online reinforcement learning method based on adaptive dynamic model for load frequency control is proposed. A low rank autoencoder feature extraction network is established to discover hidden features from the measured low-dimensional data. Based on the feature network

a sparse identification learning model for nonlinear dynamic system is established to detect the potential physical state of the dynamic model of the system and improve the online learning efficiency. Combined with model predictive control

real-time decision control is implemented. The proposed method can effectively solve the problem that traditional model predictive control depends on the accuracy of the system global model

enhance the adaptability of controller to the system dynamic model and effectively track the random fluctuation of wind power. Finally

the validity of the proposed control method is illustrated by load frequency control model integrated with type Ⅵ wind turbine.

关键词

Keywords

references

丁立 , 乔颖 , 鲁宗相 , 等 . 高比例风电对电力系统调频指标影响的定量分析 [J]. 电力系统自动化 , 2014 , 38 ( 14 ): 1 - 8 .

DING Li , QIAO Ying , LU Zongxiang , et al . Impact on frequency regulation of power system from wind power with high penetration [J]. Automation of Electric Power Systems , 2014 , 38 ( 14 ): 1 - 8 .

孙辉 , 徐箭 , 孙元章 , 等 . 基于混合整数线性规划的风电场有功优化调度 [J]. 电力系统自动化 , 2016 , 40 ( 22 ): 27 - 33 .

SUN Hui , XU Jian , SUN Yuanzhang , et al . Active power optimization scheduling of wind farm based on mixed-integer linear programming [J]. Automation of Electric Power Systems , 2016 , 40 ( 22 ): 27 - 33 .

韩民晓 , 崔军立 , 姚蜀军 , 等 . 大量风电引入电网时的频率控制特性 [J]. 电力系统自动化 , 2008 , 32 ( 1 ): 29 - 33 .

HAN Minxiao , CUI Junli , YAO Shujun , et al . Frequency control characteristics for a power system with large amounts of wind power [J]. Automation of Electric Power Systems , 2008 , 32 ( 1 ): 29 - 33 .

杨超 , 姚伟 , 文劲宇 . 基于事件驱动的含风电互联电网负荷频率鲁棒控制 [J]. 电力系统自动化 , 2018 , 42 ( 16 ): 57 - 64 .

YANG Chao , YAO Wei , WEN Jinyu . Event triggering based robust control of load frequency for interconnected power grid with wind power [J]. Automation of Electric Power Systems , 2018 , 42 ( 16 ): 57 - 64 .

YOUSEF H A , AL-KHARUSI K , ALBADI M H , et al . Load frequency control of a multi-area power system: an adaptive fuzzy logic approach [J]. IEEE Transactions on Power Systems , 2014 , 29 ( 4 ): 1822 - 1830 .

LIAO K , XU Y . A robust load frequency control scheme for power systems based on second-order sliding mode and extended disturbance observer [J]. IEEE Transactions on Industrial Informatics , 2018 , 14 ( 7 ): 3076 - 3086 .

廖小兵 , 刘开培 , 汪宁渤 , 等 . 含风电的交直流互联电网AGC两级分层模型预测控制 [J]. 电力系统自动化 , 2018 , 42 ( 8 ): 45 - 50 .

LIAO Xiaobing , LIU Kaipei , WANG Ningbo , et al . Two-level hierarchical model predictive control for AGC of AC/DC interconnected power grid with integration of wind power [J]. Automation of Electric Power Systems , 2018 , 42 ( 8 ): 45 - 50 .

左剑 , 谢平平 , 李银红 , 等 . 基于智能优化算法的互联电网负荷频率控制器设计及其控制性能分析 [J]. 电工技术学报 , 2018 , 33 ( 3 ): 478 - 489 .

ZUO Jian , XIE Pingping , LI Yinhong , et al . Intelligent optimization algorithm based load frequency controller design and its control performance assessment in interconnected power grids [J]. Transactions of China Electrotechnical Society , 2018 , 33 ( 3 ): 478 - 489 .

YAN Z M , XU Y . Data-driven load frequency control for stochastic power systems: a deep reinforcement learning method with continuous action search [J]. IEEE Transactions on Power Systems , 2019 , 34 ( 2 ): 1653 - 1656 .

SINGH V P , KISHOR N , SAMUEL P . Distributed multi-agent system-based load frequency control for multi-area power system in smart grid [J]. IEEE Transactions on Industrial Electronics , 2017 , 64 ( 6 ): 5151 - 5160 .

YIN L F , YU T , ZHOU L , et al . Artificial emotional reinforcement learning for automatic generation control of large-scale interconnected power grids [J]. IET Generation , Transmission & Distribution , 2017 , 11 ( 9 ): 2305 - 2313 .

TAKENS F . Detecting strange attractors in turbulence [M]. Heidelberg : Springer Berlin Heidelberg , 1981 .

WALLOT S , MØNSTER D . Calculation of average mutual information (AMI) and false-nearest neighbors (FNN) for the estimation of embedding parameters of multidimensional time series in Matlab [J]. Frontiers in Psychology , 2018 , 9 : 1679 .

LI Jingjing , JING Mengmeng , LU Ke , et al . From zero-shot learning to cold-start recommendation [EB/OL]. [ 2019-08-24 ]. https://arxiv.org/abs/1906.08511?context=cs https://arxiv.org/abs/1906.08511?context=cs .

BRUNTON S L , PROCTOR J L , KUTZ J N . Discovering governing equations from data by sparse identification of nonlinear dynamical systems [J]. Proceedings of the National Academy of Sciences of the United States of America , 2016 , 113 ( 15 ): 3932 - 3937 .

LI R , YANG F . A sequential least squares method for poisson equation using a patch reconstructed space [EB/OL]. [ 2019-08-24 ]. https://arxiv.org/abs/1901.06485?context=math.NA https://arxiv.org/abs/1901.06485?context=math.NA .

ROSS S , GORDON G J , BAGNELL D . A reduction of imitation learning and structured prediction to no-regret online learning [EB/OL]. [ 2019-08-24 ]. https://arxiv.org/abs/1011.0686 https://arxiv.org/abs/1011.0686 .

杨德友 , 蔡国伟 . 含规模化风电场/群的互联电网负荷频率广域分散预测控制 [J]. 中国电机工程学报 , 2015 , 35 ( 3 ): 583 - 591 .

YANG Deyou , CAI Guowei . Decentralized model predictive control based load frequency control for high wind power penetrated power systems [J]. Proceedings of the CSEE , 2015 , 35 ( 3 ): 583 - 591 .

陈来军 , 王任 , 郑天文 , 等 . 改善独立微网频率动态特性的虚拟同步发电机模型预测控制 [J]. 电力系统自动化 , 2018 , 42 ( 3 ): 40 - 47 .

CHEN Laijun , WANG Ren , ZHENG Tianwen , et al . Model predictive control of virtual synchronous generator to improve dynamic characteristic of frequency for isolated microgrid [J]. Automation of Electric Power Systems , 2018 , 42 ( 3 ): 40 - 47 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Bi-level Energy Scheduling Strategy for Hydrogen-powered Ships Combined with Multi-step Load Forecasting

Regulation Strategy of Waste Heat Compensation System for Data Center Considering Thermo-Electric Load Mismatch

Related Author

FANG Yan

LI Jinghua

LAN Fei

XIE Lingling

LAI Yening

FANG Yan

LI Jinghua

LAN Fei

Related Institution

Guangxi Key Laboratory of Power System Optimization and Energy Technology (Guangxi University)

State Grid Electric Power Research Institute (NARI Group Corporation)

Key Laboratory of Guangxi Electric Power System Optimization and Energy-saving Technologys (Guangxi University)

School of Electrical Engineering, Shandong University

College of Information Science and Engineering, Northeastern University

⁰