This is the authors' abstract. We don't add key points for this paper.
The growing adoption of wind energy resources has demonstrated notable benefits in combating climate change. Mobile wind turbines (MWTs) are uniquely positioned to navigate transportation systems, being towed by trucks, and supply energy to power distribution systems (PDSs). This flexibility enables MWTs to serve as emergency power sources, thereby contributing to enhancing the system resilience by facilitating service restoration following extreme events. This paper presents a novel framework based on Multi-agent Deep Reinforcement Learning (MADRL) to dispatch MWTs for service restoration. Deep Q-learning (DQL) and Double Deep Q-learning (DDQL) approaches are implemented within the agent for training and comparison purposes. Additionally, an action limitation is incorporated into the proposed framework in order to mitigate the influence of wind power fluctuations. Case studies conducted on an integrated power-transport system, comprising a Sioux Falls transportation system and four IEEE 33-bus test systems, illustrate the effectiveness of the proposed restoration scheduling policy in enhancing PDSs' resilience against disasters.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: