A multi-period reactive power regulation method based on proximal policy optimization

Pei Zhang; Zhujun Zhu; Honghao Li; Xiaofei Liu

doi:10.1117/12.2640487

19 October 2022 A multi-period reactive power regulation method based on proximal policy optimization

Pei Zhang, Zhujun Zhu, Honghao Li, Xiaofei Liu

Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 1229464 (2022) https://doi.org/10.1117/12.2640487
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China

Abstract

The fluctuations of renewable energies and loads pose a great challenge to reactive power regulation. Considering the time-varying characteristics of new energies and loads, the multi-time reactive power regulation problem is constructed as a reinforcement learning problem. A constraint-objective partitioning and objective preconditioning approach is proposed to design the reward function, and a proximal policy optimization algorithm is used to solve the reinforcement learning problem and obtain the reactive power regulation policy. A case study is carried out with the improved IEEE39 system, and the results show that the proposed reward function can improve the convergence speed of the agent, and the reactive power regulation strategy solved based on reinforcement learning outperforms the traditional deterministic optimization algorithm in terms of decision effect and decision time.

Citation Download Citation

Pei Zhang, Zhujun Zhu, Honghao Li, and Xiaofei Liu "A multi-period reactive power regulation method based on proximal policy optimization", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 1229464 (19 October 2022); https://doi.org/10.1117/12.2640487

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available