Game-Theoretic Resilience Framework for Cyber-Physical Microgrids using Multi-Agent Reinforcement Learning

2025-09-10

AI Summary

To address the insufficient resilience of microgrids against targeted cyberattacks—including static, severe, and adaptive attacks—this paper proposes a resilient defense framework integrating game theory and multi-agent reinforcement learning. We innovatively employ the Analytic Hierarchy Process (AHP) to synthesize multidimensional quantitative resilience metrics (e.g., load supply ratio and critical load resilience) into a Stackelberg game payoff matrix, formalized as a finite-horizon Markov decision process with guaranteed convergence. Defense strategies are co-optimized via multi-agent Q-learning coupled with regret-matching algorithms to enable adaptive, real-time evolution of both attack and defense policies. Experimental evaluation on a modified IEEE 33-bus system demonstrates that the proposed method improves system resilience by 18.7% ± 2.1% over static defense baselines, while ensuring theoretical convergence and scalability to larger networks.

Technology Category

• Multiagent Systems: Adversarial Agents
• Game Theory and Economic Paradigms: Adversarial Learning
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

The increasing reliance on cyber physical infrastructure in modern power systems has amplified the risk of targeted cyber attacks, necessitating robust and adaptive resilience strategies. This paper presents a mathematically rigorous game theoretic framework to evaluate and enhance microgrid resilience using a combination of quantitative resilience metrics Load Served Ratio LSR, Critical Load Resilience CLR, Topological Survivability Score TSS, and DER Resilience Score DRS. These are integrated into a unified payoff matrix using the Analytic Hierarchy Process AHP to assess attack defense interactions. The framework is formalized as a finite horizon Markov Decision Process MDP with formal convergence guarantees and computational complexity bounds. Three case studies are developed 1. static attacks analyzed via Nash equilibrium, 2. severe attacks incorporating high impact strategies, and 3. adaptive attacks using Stackelberg games, regret matching, softmax heuristics, and Multi Agent Q Learning. Rigorous theoretical analysis provides convergence proofs with explicit rates , PAC learning sample complexity bounds, and computational complexity analysis. The framework is tested on an enhanced IEEE 33bus distribution system with DERs and control switches, demonstrating the effectiveness of adaptive and strategic defenses in improving cyber physical resilience with statistically significant improvements of 18.7% 2.1% over static approaches.

Problem

• Developing game-theoretic resilience framework against cyber attacks in microgrids
• Integrating quantitative metrics to assess attack-defense interactions in power systems
• Formalizing adaptive defense strategies using multi-agent reinforcement learning

Innovation

• Game-theoretic framework with multi-agent reinforcement learning
• Integrated quantitative metrics via Analytic Hierarchy Process
• Markov Decision Process with formal convergence guarantees