SARIMAX-Based Power Outage Prediction During Extreme Weather Events

2025-11-02

AI Summary

To address low prediction accuracy and poor robustness in short-term power outage forecasting under extreme weather conditions, this paper proposes an enhanced SARIMAX framework tailored for 24–48-hour forecasting horizons. Methodologically, it introduces a two-stage feature engineering pipeline: (i) integration of meteorological variables with multi-scale lagged features, augmented by time embeddings and external variable incorporation; and (ii) feature refinement via correlation-based filtering and sequence optimization. A novel hierarchical fitting mechanism is proposed, enabling automatic fallback to ARIMA or historical mean models when model assumptions are violated—thereby substantially improving stability. Evaluated on real-world power grid data, the framework achieves an RMSE of 177.2, representing an 8.4% improvement over baseline methods. It demonstrates markedly enhanced prediction reliability and generalization capability across diverse weather scenarios.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

This study develops a SARIMAX-based prediction system for short-term power outage forecasting during extreme weather events. Using hourly data from Michigan counties with outage counts and comprehensive weather features, we implement a systematic two-stage feature engineering pipeline: data cleaning to remove zero-variance and unknown features, followed by correlation-based filtering to eliminate highly correlated predictors. The selected features are augmented with temporal embeddings, multi-scale lag features, and weather variables with their corresponding lags as exogenous inputs to the SARIMAX model. To address data irregularity and numerical instability, we apply standardization and implement a hierarchical fitting strategy with sequential optimization methods, automatic downgrading to ARIMA when convergence fails, and historical mean-based fallback predictions as a final safeguard. The model is optimized separately for short-term (24 hours) and medium-term (48 hours) forecast horizons using RMSE as the evaluation metric. Our approach achieves an RMSE of 177.2, representing an 8.4% improvement over the baseline method (RMSE = 193.4), thereby validating the effectiveness of our feature engineering and robust optimization strategy for extreme weather-related outage prediction.

Problem

• Predicting power outages during extreme weather events
• Developing SARIMAX-based short-term outage forecasting system
• Improving prediction accuracy through feature engineering and optimization

Innovation

• SARIMAX model with exogenous weather inputs
• Two-stage feature engineering with temporal embeddings
• Hierarchical fitting strategy with fallback predictions