Fast frequency response for centralized renewable energy source stations based on deep reinforcement learning

Wei Wang; Haiyun Wang; Zhijian Zhang; Lei Zhang; Cheng Wang

doi:10.1117/12.3004411

25 September 2023 Fast frequency response for centralized renewable energy source stations based on deep reinforcement learning

Wei Wang, Haiyun Wang, Zhijian Zhang, Lei Zhang, Cheng Wang

Author Affiliations +

Proceedings Volume 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023); 127880Z (2023) https://doi.org/10.1117/12.3004411
Event: Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 2023, Kuala Lumpur, Malaysia

Abstract

As large-scale renewable energy sources are connected to the power system, the scale of centralized renewable energy sources stations is constantly expanding. More and more attention is paid to the problem of collaborative frequency control among power sources with different response capabilities. The droop control response mechanism that mimics the synchrotron design lacks flexibility. The emerging deep reinforcement learning method provides a new idea for the frequency control of renewable energy-based power systems. In this paper, a mathematical model describing the response characteristics of each power supply and the nonlinear characteristics of dead zones and limiting zones is constructed via mechanism analysis. In addition, an optimization objective function considering the frequency modulation performance and economy of renewable energy supplies is proposed, and the control strategy optimization problem is solved based on the twin-delayed deep deterministic policy gradient algorithm. Case studies show that the proposed method can effectively improve the transient frequency characteristics of the system and realize the cooperative participation of renewable energy sources with different dynamic characteristics with fast frequency responses.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Wei Wang, Haiyun Wang, Zhijian Zhang, Lei Zhang, and Cheng Wang "Fast frequency response for centralized renewable energy source stations based on deep reinforcement learning", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 127880Z (25 September 2023); https://doi.org/10.1117/12.3004411

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