Show simple item record

AuthorYang, Fan
AuthorHuang, Dong Hua
AuthorLi, Dongdong
AuthorLin, Shunfu
AuthorMuyeen, S. M.
AuthorZhai, Haibao
Available date2023-02-23T12:04:39Z
Publication Date2022-01-01
Publication NameIEEE Transactions on Power Systems
Identifierhttp://dx.doi.org/10.1109/TPWRS.2022.3223255
CitationYang, F., Huang, D., Li, D., Lin, S., Muyeen, S. M., & Zhai, H. (2022). Data-Driven Load Frequency Control Based on Multi-Agent Reinforcement Learning With Attention Mechanism. IEEE Transactions on Power Systems.‏
ISSN08858950
URIhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85144075792&origin=inward
URIhttp://hdl.handle.net/10576/40348
AbstractWith the massive penetration of renewable energy, traditional reinforcement learning algorithms suffer from slow convergence and area control error (ACE) in interconnected power systems. This paper proposes data-driven load frequency control (LFC) based on multi-agent reinforcement learning with attention mechanism in interconnected power systems. It can be divided into two phases; in the centralized training, the agents are trained by an experience replay mechanism; in the decentralized execution, the trained agent automatically regulates the generation power to control the load frequency by real-time access to the grid data in the area. The agent can selectively focus on specific information in the environment by introducing a criticism network with an attention mechanism. The attention mechanism can reduce the training time for reinforcement learning while improving control performance under disturbance. A novel reward function based on a cooperation mechanism is used to score the performance of agent, which can guide the reinforcement learning algorithm to reduce the ACE of each area simultaneously. The proposed method is validated by the IEEE three-area interconnected power system, and it is concluded that the method can reduce the ACE caused by load and renewable power disturbances, and greatly reduce the training time of the algorithm.
Languageen
PublisherInstitute of Electrical and Electronics Engineers Inc.
SubjectArea control error
attention mechanism
Frequency control
Generators
interconnected power system
load frequency control
Mathematical models
multi-agent reinforcement learning
Power systems
Reinforcement learning
Renewable energy sources
Training
TitleData-Driven Load Frequency Control Based on Multi-Agent Reinforcement Learning With Attention Mechanism
TypeArticle
Pagination1-11
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record