Interpretable Kolmogorov-Arnold Network with Feature-Isolated Temporal Attention Mechanism for Electricity Load Forecasting

2026-06-22

AI Summary

This study addresses the limited interpretability of existing deep learning models for load forecasting and the inability of Kolmogorov–Arnold Networks (KANs) to effectively capture complex temporal dynamics. To overcome these challenges, the authors propose LoadKAN, a novel framework that integrates a feature-isolating temporal attention mechanism with KAN. The attention module independently extracts dynamic patterns from distinct input features—such as historical load and human mobility—while KAN employs learnable activation functions to model their nonlinear, market-specific relationships with electricity demand. Evaluated on three U.S. electricity market datasets, LoadKAN achieves prediction accuracy comparable to state-of-the-art black-box models. Furthermore, sensitivity analyses quantify the influence of six categories of mobility patterns, yielding interpretable insights unattainable with conventional approaches.

Abstract

Accurate electricity load forecasting is a crucial prerequisite for stable power system operations. While prevalent deep learning models present competitive performance, they often operate as black boxes and lack interpretability. While the Kolmogorov-Arnold network (KAN) has emerged as a promising alternative because of its learnable activation function design, its direct application to time-series forecasting faces challenges in modeling complex temporal data patterns. Also, simple integration into existing architectures, such as serving as replacement of neural modules, cannot fully leverage KAN's interpretability strengths. To address these gaps, this study develops LoadKAN, a novel hybrid and interpretable framework for load forecasting that synergistically combines a specifically-designed feature-isolated temporal attention mechanism with a KAN module. The attention stage aims to extract temporal dynamics from each input feature independently, such as historical load and human mobility, providing distilled feature representations to the KAN module for interpretable predictions. When evaluated on datasets from three representative U.S. electricity markets, our LoadKAN remains highly competitive when compared to extensively-tuned, state-of-the-art, black-box deep learning benchmarks. More importantly, LoadKAN's interpretability enables a granular analysis of the learned non-linear relationships between six distinct mobility patterns and electricity load. Through KAN-learned activation functions, our quantitative sensitivity analyses on mobility features reveal complex and market-specific dependencies. These findings further demonstrate the ability of our LoadKAN to generate insights often obscured by opaque black-box neural forecasting models.

Problem

• electricity load forecasting
• interpretability
• Kolmogorov-Arnold network
• temporal attention
• time-series forecasting

Innovation

• Kolmogorov-Arnold Network
• Interpretable AI
• Temporal Attention Mechanism
• Feature-Isolated Representation
• Electricity Load Forecasting