Interpretable Physics-Informed Load Forecasting for U.S. Grid Resilience: SHAP-Guided Ensemble Validation in Hybrid Deep Learning Under Extreme Weather
📰 ArXiv cs.AI
Learn to build an interpretable physics-informed load forecasting model using SHAP-guided ensemble validation and hybrid deep learning for U.S. grid resilience under extreme weather
Action Steps
- Build a Convolutional Neural Network (CNN) branch for local feature extraction
- Implement a Transformer branch for long-range dependency modeling
- Fuse the CNN and Transformer branches through a unified framework
- Apply SHAP-guided ensemble validation to improve model interpretability
- Test the model under extreme weather conditions to evaluate its performance
Who Needs to Know This
Data scientists and engineers working on grid resilience and load forecasting can benefit from this approach to improve the accuracy and interpretability of their models
Key Insight
💡 Interpretable physics-informed load forecasting can improve operator trust and grid resilience under extreme weather conditions
Share This
🚀 Improve U.S. grid resilience with interpretable physics-informed load forecasting using SHAP-guided ensemble validation and hybrid deep learning! #AI #LoadForecasting
Full Article
Title: Interpretable Physics-Informed Load Forecasting for U.S. Grid Resilience: SHAP-Guided Ensemble Validation in Hybrid Deep Learning Under Extreme Weather
Abstract:
arXiv:2604.23500v1 Announce Type: cross Abstract: Accurate short-term electricity load forecasting is a cornerstone of U.S. grid reliability; however, prevailing deep learning models remain opaque, limiting operator trust during extreme weather. A unified, interpretable, physics-informed ensemble framework is proposed, integrating a Convolutional Neural Network (CNN) branch for local feature extraction and a Transformer branch for long-range dependency modeling; the branches are fused through a
Abstract:
arXiv:2604.23500v1 Announce Type: cross Abstract: Accurate short-term electricity load forecasting is a cornerstone of U.S. grid reliability; however, prevailing deep learning models remain opaque, limiting operator trust during extreme weather. A unified, interpretable, physics-informed ensemble framework is proposed, integrating a Convolutional Neural Network (CNN) branch for local feature extraction and a Transformer branch for long-range dependency modeling; the branches are fused through a
DeepCamp AI