Demonstrating Safe Deep Reinforcement Learning Based Coordinated Frequency Control in East China Power Grid

View at publisher Summarise with VIRAT
Authors: Yang Zhou, Liangcai Zhou, Mengjie Guo
Cited by: 0
References: 22

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The rapid integration of renewable energy introduces challenges for frequency control in large-scale power systems, as traditional automatic generation control (AGC) methods, particularly those based on optimal power flow (OPF), struggle with network constraints, computational delays, and real-time adaptability. This paper presents a safe and scalable frequency control framework based on deep reinforcement learning (DRL), designed to enhance stability, safety, and scalability in interconnected grids. Unlike existing DRL-based AGC methods, our approach explicitly incorporates safety constraints on tie-line flows and operational limits, ensuring robust and reliable control decisions. Validated using real-world data from the East China Power Grid, the proposed framework enables fast, adaptive, and safety-aware frequency regulation, reducing reliance on manual interventions.

Fields of Study & Subjects

Frequency Control in Power Systems Microgrid Control and Optimization Electric Power System Optimization

Publication details

Journal / source
IEEE PES International Meeting (PES IM)
Pages
1–5
Publication date
18 January 2026
Language
EN