4.7 Article

A Barrier-Certificated Reinforcement Learning Approach for Enhancing Power System Transient Stability

Journal

IEEE TRANSACTIONS ON POWER SYSTEMS
Volume 38, Issue 6, Pages 5356-5366

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TPWRS.2022.3233770

Keywords

Power system stability; Safety; Stability analysis; Reinforcement learning; Neural networks; Power system control; safe reinforcement learning; control barrier functions; neural networks; power system control

Ask authors/readers for more resources

This paper proposes a general solution framework for traditional control problems in modern power systems. The framework consists of a model-free controller and a barrier-certification system, which utilize reinforcement learning and control barrier functions. Neural networks are used to represent the barrier function, addressing the challenge of calculating it for complex power systems. The effectiveness of the proposed framework is demonstrated through several case studies.
Increasing integration of renewable resources brings more flexibility and poses new challenges to modern power systems, leading to highly nonlinear and complex dynamics. This paper aims to provide a general solution framework to traditional control problems, such as frequency control and voltage control, which attempt to maintain the stability of either synchronous generators-governed or inverter-governed systems when subjected to a disturbance and simultaneously guarantee operational constraints, providing a complete complement to existing works on control design. Building on reinforcement learning (RL) and control barrier functions, the framework includes two subsystems, i.e., a model-free controller and a barrier-certification system, which discover RL-based control actions and sequentially filter them using a barrier certificate to satisfy operational constraints. Calculating a barrier function is generally challenging for a complex power system. This is addressed by representing the barrier function using neural networks (NNs) and data-based approaches. An adaptive method is introduced to certify the neural barrier function that perseveres barrier conditions, which is more compatible with online implementation. The proposed framework synthesizes a stabilizing controller that satisfies predefined safety regions. The effectiveness of the proposed framework is demonstrated via several comparative case studies.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available