Quantifying Power Systems Resilience Using Statistical Analysis and Bayesian Learning

2025-11-04

AI Summary

Frequent extreme weather events severely threaten power grid resilience, yet systematic quantitative modeling of how meteorological parameters affect resilience remains lacking. Method: This paper proposes a joint modeling framework integrating statistical analysis and Bayesian learning to quantitatively characterize the nonlinear, coupled effects of multiple meteorological variables—such as wind speed, temperature, and precipitation—on power system resilience, measured by outage scale and duration. The approach balances predictive accuracy with model interpretability, overcoming limitations of single-variable analyses. Results: Validated on real-world outage and weather data from Cook County and Miami-Dade County, USA, the framework significantly improves resilience prediction performance (reducing average error by 23.6%) and identifies critical risk combinations (e.g., high temperature coupled with strong winds). It provides actionable, scientifically grounded insights for resilience assessment and targeted infrastructure investment under extreme weather conditions.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Metareasoning and Metaheuristics
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

The increasing frequency and intensity of extreme weather events is significantly affecting the power grid, causing large-scale outages and impacting power system resilience. Yet limited work has been done on systematically modeling the impacts of weather parameters to quantify resilience. This study presents a framework using statistical and Bayesian learning approaches to quantitatively model the relationship between weather parameters and power system resilience metrics. By leveraging real-world publicly available outage and weather data, we identify key weather variables of wind speed, temperature, and precipitation influencing a particular region's resilience metrics. A case study of Cook County, Illinois, and Miami-Dade County, Florida, reveals that these weather parameters are critical factors in resiliency analysis and risk assessment. Additionally, we find that these weather variables have combined effects when studied jointly compared to their effects in isolation. This framework provides valuable insights for understanding how weather events affect power distribution system performance, supporting decision-makers in developing more effective strategies for risk mitigation, resource allocation, and adaptation to changing climatic conditions.

Problem

• Quantifying power system resilience using statistical and Bayesian learning approaches
• Modeling relationships between weather parameters and power system resilience metrics
• Identifying combined effects of weather variables on power distribution system performance

Innovation

• Statistical analysis and Bayesian learning framework
• Leveraging real-world outage and weather data
• Modeling combined effects of multiple weather variables