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

• URL: http://arxiv.org/abs/2508.04780v1
• Date: Wed, 06 Aug 2025 18:00:30 GMT
• Title: Uncertainty-aware Predict-Then-Optimize Framework for Equitable Post-Disaster Power Restoration
• Authors: Lin Jiang, Dahai Yu, Rongchao Xu, Tian Tang, Guang Wang,
• Abstract summary: Extreme weather events, such as hurricanes, highlight the urgent need for efficient and equitable power system restoration.<n>Our data-driven analysis reveals significant disparities in request submission volume, as disadvantaged communities tend to submit fewer restoration requests.<n>We propose an equity-aware power restoration strategy that balances both restoration efficiency and equity across communities.
• Score: 7.932119348792331
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Observationally Informed Adaptive Causal Experimental Design [55.998153710215654]
  We propose Active Residual Learning, a new paradigm that leverages the observational model as a foundational prior.<n>This approach shifts the experimental focus from learning target causal quantities from scratch to efficiently estimating the residuals required to correct observational bias.<n> Experiments on synthetic and semi-synthetic benchmarks demonstrate that R-Design significantly outperforms baselines.
  arXiv  Detail & Related papers  (2026-03-04T06:52:37Z)
• What Makes Value Learning Efficient in Residual Reinforcement Learning? [57.635661297706065]
  Residual reinforcement learning (RL) enables stable online refinement of expressive pretrained policies by freezing the base and learning only bounded corrections.<n>In this work, we identify two key bottlenecks: cold start pathology, where the critic lacks knowledge of the value landscape around the base policy, and structural scale mismatch.<n>We propose DAWN, a minimal approach targeting efficient value learning in residual RL.
  arXiv  Detail & Related papers  (2026-02-11T05:25:39Z)
• Multivariate LSTM-Based Forecasting for Renewable Energy: Enhancing Climate Change Mitigation [0.0]
  This paper introduces a multivariate Long Short-Term Memory (LSTM)-based network designed to forecast RESs generation using their real-world historical data.<n>The proposed model effectively captures long-term dependencies and interactions between different RESs, utilizing historical data from both local and neighboring areas.<n>In the case study, we showed that the proposed forecasting approach results in lower CO2 emissions, and a more reliable supply of electric loads.
  arXiv  Detail & Related papers  (2026-01-16T03:01:46Z)
• Reinforcement Learning for Micro-Level Claims Reserving [1.2613956492162683]
  We formulate individual claims reserving as a claim-level Markov decision process.<n>We learn from all observed claim trajectories, including claims that remain open at valuation.<n>On CAS and SPLICE synthetic general insurance datasets, the proposed Soft Actor-Critic implementation delivers competitive claim-level accuracy.
  arXiv  Detail & Related papers  (2026-01-12T15:17:18Z)
• Rediscovering Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning [55.59724323303857]
  We propose a framework that balances exploration and exploitation via three components: difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment.<n>Experiments on multiple mathematical reasoning benchmarks show that AER consistently outperforms baselines, improving both reasoning accuracy and exploration capability.
  arXiv  Detail & Related papers  (2025-10-13T03:10:26Z)
• LRPO: Enhancing Blind Face Restoration through Online Reinforcement Learning [54.51101908523586]
  Blind Face Restoration (BFR) encounters inherent challenges in exploring its large solution space.<n>We propose a Likelihood-Regularized Policy Optimization (LRPO) framework, the first to apply online reinforcement learning (RL) to the BFR task.<n>Our proposed LRPO significantly improves the face restoration quality over baseline methods and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-09-27T14:42:29Z)
• Quantifying the Social Costs of Power Outages and Restoration Disparities Across Four U.S. Hurricanes [7.3500083125434195]
  This study applies to four United States hurricanes, Beryl 2024 Texas, Helene 2024 Florida, Milton 2024 Florida, and Ida 2021 Louisiana.<n>Results demonstrate regressive patterns with greater burdens in lower income areas.<n>This framework delivers a transferable method for assessing outage impacts and equity.
  arXiv  Detail & Related papers  (2025-09-02T14:32:08Z)
• ASTER: Adaptive Spatio-Temporal Early Decision Model for Dynamic Resource Allocation [9.870286663826253]
  In emergency response, the priority is successful resource allocation and intervention, not just incident prediction.<n>It is essential to propose an Adaptive S-temporal Decision (ASTER) that reforms the forecasting paradigm from event anticipation to actionable decision support.<n>This framework ensures that information is directly used for decision-making, thereby maximizing overall effectiveness.
  arXiv  Detail & Related papers  (2025-06-22T07:49:37Z)
• Adaptive Robust Optimization with Data-Driven Uncertainty for Enhancing Distribution System Resilience [6.325705102716997]
  Extreme weather events are placing strain on electric power systems, exposing the limitations of purely reactive responses.<n>This paper proposes a novel tri-level optimization framework that integrates proactive infrastructure investment and reactive response.<n> Experiments on both real and synthetic data demonstrate that our approach consistently outperforms conventional two-stage methods.
  arXiv  Detail & Related papers  (2025-05-16T18:43:31Z)
• ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning [75.1101108949743]
  Large Reasoning Models (LRMs) perform strongly in complex reasoning tasks via Chain-of-Thought (CoT) prompting.<n>LRMs often suffer from verbose outputs caused by redundant content, increasing computational overhead, and degrading user experience.<n>We propose ConCISE, a framework that simplifies reasoning chains by reinforcing the model's confidence during inference.
  arXiv  Detail & Related papers  (2025-05-08T01:40:40Z)
• A Simulation-Based Framework for Leveraging Shared Autonomous Vehicles to Enhance Disaster Evacuations in Rural Regions with a Focus on Vulnerable Populations [0.210674772139335]
  This study proposes a framework to deploy SAVs in pre- and post-disaster evacuations in rural areas.<n>The framework prioritizes the needs of vulnerable groups, including individuals with disabilities, limited English proficiency, and elderly residents.
  arXiv  Detail & Related papers  (2025-01-20T00:12:31Z)
• Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages [56.98243487769916]
  Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning. We propose Adaptive RR, which dynamically adjusts the replay ratio based on the critic's plasticity level.
  arXiv  Detail & Related papers  (2023-10-11T12:05:34Z)
• A Stochastic Online Forecast-and-Optimize Framework for Real-Time Energy Dispatch in Virtual Power Plants under Uncertainty [18.485617498705736]
  We propose a real-time uncertainty-aware energy dispatch framework, which is composed of two key elements. The proposed framework is capable to rapidly adapt to the real-time data distribution, as well as to target on uncertainties caused by data drift, model discrepancy and environment perturbations in the control process. The framework won the championship in CityLearn Challenge 2022, which provided an influential opportunity to investigate the potential of AI application in the energy domain.
  arXiv  Detail & Related papers  (2023-09-15T00:04:00Z)
• An Asymmetric Loss with Anomaly Detection LSTM Framework for Power Consumption Prediction [1.6156983514505385]
  Power consumption patterns of the residential sector contain fluctuations and anomalies making them challenging to predict. We propose multiple Long Short-Term Memory (LSTM) frameworks with different asymmetric loss functions to impose a higher penalty on underpredictions. Considering the effect of weather and social factors, seasonality splitting is performed on the three considered datasets from France, Germany, and Hungary.
  arXiv  Detail & Related papers  (2023-02-05T17:16:15Z)
• Relationship Quantification of Image Degradations [72.98190570967937]
  Degradation Relationship Index (DRI) is defined as the mean drop rate difference in the validation loss between two models. DRI always predicts performance improvement by using the specific degradation as an auxiliary to train models. We propose a simple but effective method to estimate whether the given degradation combinations could improve the performance on the anchor degradation.
  arXiv  Detail & Related papers  (2022-12-08T09:05:19Z)
• Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO [66.5384483339413]
  We present a new monotonic improvement guarantee for optimizing decentralized policies in cooperative Multi-Agent Reinforcement Learning (MARL) We show that a trust region constraint can be effectively enforced in a principled way by bounding independent ratios based on the number of agents in training.
  arXiv  Detail & Related papers  (2022-01-31T20:39:48Z)
• Implicit Subspace Prior Learning for Dual-Blind Face Restoration [66.67059961379923]
  A novel implicit subspace prior learning (ISPL) framework is proposed as a generic solution to dual-blind face restoration. Experimental results demonstrate significant perception-distortion improvement of ISPL against existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-10-12T08:04:24Z)
• Deep Learning-based Resource Allocation for Infrastructure Resilience [0.5249805590164901]
  Decision-makers can use our trained models to allocate resources more efficiently after contingencies. We showcase our methodology by the real-world interdependent infrastructure of Shelby County, TN.
  arXiv  Detail & Related papers  (2020-07-12T00:48:15Z)
• GenDICE: Generalized Offline Estimation of Stationary Values [108.17309783125398]
  We show that effective estimation can still be achieved in important applications. Our approach is based on estimating a ratio that corrects for the discrepancy between the stationary and empirical distributions. The resulting algorithm, GenDICE, is straightforward and effective.
  arXiv  Detail & Related papers  (2020-02-21T00:27:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.