Decentralized coordinated emergency frequency control strategy for renewables-rich power systems based on multi-agent reinforcement learning

With the rapid growth of renewable energy in the power system and the implementation of high-capacity LCC-HVDC projects, the frequency support capability of the grid is decreasing. Existing centralized single-measurement methods and model-based emergency frequency control (EFC) methods face signific...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhenglong Sun, Junpeng Han, Weihan Chen, Rui Zhang, Yong Liu, Yoash Levron, Juri Belikov
Format: Article
Language:English
Published: Elsevier 2025-10-01
Series:International Journal of Electrical Power & Energy Systems
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0142061525005836
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the rapid growth of renewable energy in the power system and the implementation of high-capacity LCC-HVDC projects, the frequency support capability of the grid is decreasing. Existing centralized single-measurement methods and model-based emergency frequency control (EFC) methods face significant challenges. To fill this gap, this paper proposes a renewables-rich grids EFC method for coordinating LCC-HVDC emergency power support and load shedding. Combined with the system frequency response (SFR) model parameter identification method, the grid frequency regulation capability of different fault conditions is evaluated. A MADRL algorithm with integrated SFR model is developed to overcome the problem of inaccurate assessment of centralized action values in the MADRL algorithm used for EFC, and a decentralized and cooperative EFC strategy is realized. The effectiveness and adaptability of the proposed method is demonstrated by simulating the modified IEEE 39 bus system.
ISSN:0142-0615