Real-Time Cascade Mitigation in Power Systems Using Influence Graph Improved by Reinforcement Learning

2025-06-10

AI Summary

Increasing renewable energy penetration exacerbates cascading blackout risks in power systems, posing significant challenges for real-time prevention and mitigation. Method: This paper proposes an Influence-Diagram Markov Decision Process (ID-MDP) framework integrating explicit uncertainty modeling—capturing both stochastic generation-load fluctuations and random initial faults. It extends influence diagrams to MDPs with a “no-action” option and introduces a policy-gradient reinforcement learning algorithm featuring invalid-action masking and cold-start initialization to accelerate convergence and enhance robustness. Results: Evaluated on IEEE 14- and 118-bus systems, the learned online control policy effectively suppresses cascade propagation via strategic line tripping and consistently identifies transmission lines critical for blocking cascades across diverse scenarios. The framework establishes a novel paradigm for real-time resilience-oriented control in high-renewable power grids.

Technology Category

• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)
• Reasoning under Uncertainty: Sequential Decision Making
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Despite high reliability, modern power systems with growing renewable penetration face an increasing risk of cascading outages. Real-time cascade mitigation requires fast, complex operational decisions under uncertainty. In this work, we extend the influence graph into a Markov decision process model (MDP) for real-time mitigation of cascading outages in power transmission systems, accounting for uncertainties in generation, load, and initial contingencies. The MDP includes a do-nothing action to allow for conservative decision-making and is solved using reinforcement learning. We present a policy gradient learning algorithm initialized with a policy corresponding to the unmitigated case and designed to handle invalid actions. The proposed learning method converges faster than the conventional algorithm. Through careful reward design, we learn a policy that takes conservative actions without deteriorating system conditions. The model is validated on the IEEE 14-bus and IEEE 118-bus systems. The results show that proactive line disconnections can effectively reduce cascading risk, and certain lines consistently emerge as critical in mitigating cascade propagation.

Problem

• Mitigate cascading outages in power systems with renewables
• Develop real-time MDP model for outage decisions
• Improve reinforcement learning for conservative mitigation actions

Innovation

• Reinforcement learning improves influence graph
• MDP model enables real-time cascade mitigation
• Policy gradient algorithm handles invalid actions