A Glass-Box Deep-Learning Method for Electrical Energy System Modeling Based on Kolmogorov-Arnold Network

TL;DR

This paper introduces Kolmogorov-Arnold Network (KAN), a transparent deep learning model for electrical energy systems that combines interpretability with nonlinear fitting capabilities.

Contribution

The paper proposes a novel neural network structure, KAN, with learnable activation functions and symbolic representation for improved interpretability in energy system modeling.

Findings

KAN achieves high interpretability and accuracy in modeling electrical energy systems.

Simulation results show KAN's robustness and generalization ability.

KAN effectively expresses physical processes with explicit mathematical formulas.

Abstract

Deep learning methods have been widely used as an end-to-end modeling strategy of electrical energy systems because of their conveniency and powerful pattern recognition capability. However, due to the "closed-box" nature, deep learning methods have long been blamed for their poor interpretability when modeling a physical system. In this paper, we introduce a novel neural network structure, Kolmogorov-Arnold Network (KAN), to achieve "glass-box" modeling for electrical energy systems to enhance the interpretability. The most distinct feature of KAN lies in the learnable activation function together with the sparse training and symbolification process. Consequently, KAN can express the physical process with concise and explicit mathematical formulas while remaining the nonlinear-fitting capability of deep neural networks. Simulation results based on three electrical energy systems demonstrate the effectiveness of KAN in the aspects of interpretability, accuracy, robustness and generalization ability.