Mitigating Multi-Stage Cascading Failure by Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning-based strategy to mitigate multi-stage cascading failures in power systems, demonstrating effective reduction in collapse rates through experiments on IEEE 118-bus system.

Contribution

It presents a novel RL framework tailored for MSCF mitigation, including design of rewards and states, and validates its effectiveness with neural network models.

Findings

Reduced system collapse rates in IEEE 118-bus system

Effective application of RL with shallow and deep neural networks

Promising results in cascading failure mitigation

Abstract

This paper proposes a cascading failure mitigation strategy based on Reinforcement Learning (RL) method. Firstly, the principles of RL are introduced. Then, the Multi-Stage Cascading Failure (MSCF) problem is presented and its challenges are investigated. The problem is then tackled by the RL based on DC-OPF (Optimal Power Flow). Designs of the key elements of the RL framework (rewards, states, etc.) are also discussed in detail. Experiments on the IEEE 118-bus system by both shallow and deep neural networks demonstrate promising results in terms of reduced system collapse rates.