Resilience-based post disaster recovery optimization for infrastructure system via Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning approach, specifically using Double DQN, to optimize post-earthquake recovery of infrastructure systems, improving efficiency and resilience compared to traditional methods.

Contribution

The paper develops a novel DRL-based framework for infrastructure recovery, incorporating a resilience metric and graph-based system modeling, demonstrating its effectiveness over baseline methods.

Findings

Double DQN outperforms other algorithms in recovery optimization

The proposed method reduces computational cost

Enhanced resilience and faster recovery demonstrated

Abstract

Infrastructure systems are critical in modern communities but are highly susceptible to various natural and man-made disasters. Efficient post-disaster recovery requires repair-scheduling approaches under the limitation of capped resources that need to be shared across the system. Existing approaches, including component ranking methods, greedy evolutionary algorithms, and data-driven machine learning models, face various limitations when tested within such a context. To tackle these issues, we propose a novel approach to optimize post-disaster recovery of infrastructure systems by leveraging Deep Reinforcement Learning (DRL) methods and incorporating a specialized resilience metric to lead the optimization. The system topology is represented adopting a graph-based structure, where the system's recovery process is formulated as a sequential decision-making problem. Deep Q-learning algorithms are employed to learn optimal recovery strategies by mapping system states to specific actions, as for instance which component ought to be repaired next, with the goal of maximizing long-term recovery from a resilience-oriented perspective. To demonstrate the efficacy of our proposed approach, we implement this scheme on the example of post-earthquake recovery optimization for an electrical substation system. We assess different deep Q-learning algorithms to this end, namely vanilla Deep Q-Networks (DQN), Double DQN(DDQN), Duel DQN, and duel DDQN, demonstrating superiority of the DDQN for the considered problem. A further comparative analysis against baseline methods during testing reveals the superior performance of the proposed method in terms of both optimization effect and computational cost, rendering this an attractive approach in the context of resilience enhancement and rapid response and recovery.