Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

Composite experience replay based deep reinforcement learning with application in wind farm control

Tools
- Tools
+ Tools

Dong, Hongyang and Zhao, Xiaowei (2022) Composite experience replay based deep reinforcement learning with application in wind farm control. IEEE Transactions on Control Systems Technology, 30 (3). pp. 1281-1295. doi:10.1109/TCST.2021.3102476 ISSN 1063-6536.

[img]
Preview
PDF
WRAP-Composite-experience-replay-based-deep-wind-farm-control-2021.pdf - Accepted Version - Requires a PDF viewer.

Download (9Mb) | Preview
Official URL: https://doi.org/10.1109/TCST.2021.3102476

Request Changes to record.

Abstract

In this article, a deep reinforcement learning (RL)-based control approach with enhanced learning efficiency and effectiveness is proposed to address the wind farm control problem. Specifically, a novel composite experience replay (CER) strategy is designed and embedded in the deep deterministic policy gradient (DDPG) algorithm. CER provides a new sampling scheme that can mine the information of stored transitions in-depth by making a tradeoff between rewards and temporal difference (TD) errors. Modified importance-sampling weights are introduced to the training process of neural networks (NNs) to deal with the distribution mismatching problem induced by CER. Then, our CER-DDPG approach is applied to optimizing the total power production of wind farms. The main challenge of this control problem comes from the strong wake effects among wind turbines and the stochastic features of environments, rendering it intractable for conventional control approaches. A reward regularization process is designed along with the CER-DDPG, which employs an additional NN to handle the bias of rewards caused by the stochastic wind speeds. Tests with a dynamic wind farm simulator (WFSim) show that our method achieves higher rewards with less training costs than conventional deep RL-based control approaches, and it has the ability to increase the total power generation of wind farms with different specifications.

Item Type: Journal Article
Subjects: Q Science > Q Science (General)
Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
T Technology > TJ Mechanical engineering and machinery
Divisions: Faculty of Science, Engineering and Medicine > Engineering > Engineering
Library of Congress Subject Headings (LCSH): Intelligent control systems , Wind power plants , Reinforcement learning , Neural networks (Computer science)
Journal or Publication Title: IEEE Transactions on Control Systems Technology
Publisher: IEEE
ISSN: 1063-6536
Official Date: May 2022
Dates:
DateEvent
May 2022Published
12 August 2021Available
1 August 2021Accepted
Volume: 30
Number: 3
Page Range: pp. 1281-1295
DOI: 10.1109/TCST.2021.3102476
Status: Peer Reviewed
Publication Status: Published
Reuse Statement (publisher, data, author rights): © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Access rights to Published version: Restricted or Subscription Access
Date of first compliant deposit: 14 August 2021
Date of first compliant Open Access: 17 August 2021
RIOXX Funder/Project Grant:
Project/Grant IDRIOXX Funder NameFunder ID
EP/S001905/1Engineering and Physical Sciences Research Councilhttp://dx.doi.org/10.13039/501100000266

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics

twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us