Uncertainty-aware Predict-Then-Optimize Framework for Equitable Post-Disaster Power Restoration

2025-08-06

AI Summary

Frequent extreme weather events exacerbate the tension between efficiency and fairness in post-disaster power restoration: conventional repair scheduling—relying on reported outage counts—systematically delays restoration in vulnerable communities due to their lower reporting rates. To address this, we propose EPOPR, a novel framework integrating equity-aware conformalized quantile regression (ECQR) with spatial-temporal attentional reinforcement learning (ST-ARL). ECQR enables heteroscedasticity-robust, uncertainty-quantified repair duration prediction, while ST-ARL performs region-adaptive resource allocation. Crucially, EPOPR explicitly incorporates social vulnerability metrics to mitigate decision bias arising from overreliance on low-uncertainty predictions. Experiments demonstrate that EPOPR reduces average outage duration by 3.60% and decreases inter-community restoration inequality by 14.19% relative to state-of-the-art baselines—achieving, for the first time, joint optimization of operational efficiency and procedural fairness in post-disaster electric grid restoration.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Distributed Search

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems

Abstract

The increasing frequency of extreme weather events, such as hurricanes, highlights the urgent need for efficient and equitable power system restoration. Many electricity providers make restoration decisions primarily based on the volume of power restoration requests from each region. However, our data-driven analysis reveals significant disparities in request submission volume, as disadvantaged communities tend to submit fewer restoration requests. This disparity makes the current restoration solution inequitable, leaving these communities vulnerable to extended power outages. To address this, we aim to propose an equity-aware power restoration strategy that balances both restoration efficiency and equity across communities. However, achieving this goal is challenging for two reasons: the difficulty of predicting repair durations under dataset heteroscedasticity, and the tendency of reinforcement learning agents to favor low-uncertainty actions, which potentially undermine equity. To overcome these challenges, we design a predict-then-optimize framework called EPOPR with two key components: (1) Equity-Conformalized Quantile Regression for uncertainty-aware repair duration prediction, and (2) Spatial-Temporal Attentional RL that adapts to varying uncertainty levels across regions for equitable decision-making. Experimental results show that our EPOPR effectively reduces the average power outage duration by 3.60% and decreases inequity between different communities by 14.19% compared to state-of-the-art baselines.

Problem

• Addressing inequitable power restoration in disadvantaged communities post-disasters
• Predicting repair durations under dataset heteroscedasticity challenges
• Balancing efficiency and equity in reinforcement learning-based restoration strategies

Innovation

• Equity-Conformalized Quantile Regression for uncertainty prediction
• Spatial-Temporal Attentional RL for equitable decision-making
• EPOPR framework balances efficiency and equity