{"title":"基于 Kolmogorov-Arnold 网络的电能系统建模白盒深度学习方法","authors":"Zhenghao Zhou, Yiyan Li, Zelin Guo, Zheng Yan, Mo-Yuen Chow","doi":"arxiv-2409.08044","DOIUrl":null,"url":null,"abstract":"Deep learning methods have been widely used as an end-to-end modeling\nstrategy of electrical energy systems because of their conveniency and powerful\npattern recognition capability. However, due to the \"black-box\" nature, deep\nlearning methods have long been blamed for their poor interpretability when\nmodeling a physical system. In this paper, we introduce a novel neural network\nstructure, Kolmogorov-Arnold Network (KAN), to achieve \"white-box\" modeling for\nelectrical energy systems to enhance the interpretability. The most distinct\nfeature of KAN lies in the learnable activation function together with the\nsparse training and symbolification process. Consequently, KAN can express the\nphysical process with concise and explicit mathematical formulas while\nremaining the nonlinear-fitting capability of deep neural networks. Simulation\nresults based on three electrical energy systems demonstrate the effectiveness\nof KAN in the aspects of interpretability, accuracy, robustness and\ngeneralization ability.","PeriodicalId":501034,"journal":{"name":"arXiv - EE - Signal Processing","volume":"106 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A White-Box Deep-Learning Method for Electrical Energy System Modeling Based on Kolmogorov-Arnold Network\",\"authors\":\"Zhenghao Zhou, Yiyan Li, Zelin Guo, Zheng Yan, Mo-Yuen Chow\",\"doi\":\"arxiv-2409.08044\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Deep learning methods have been widely used as an end-to-end modeling\\nstrategy of electrical energy systems because of their conveniency and powerful\\npattern recognition capability. However, due to the \\\"black-box\\\" nature, deep\\nlearning methods have long been blamed for their poor interpretability when\\nmodeling a physical system. In this paper, we introduce a novel neural network\\nstructure, Kolmogorov-Arnold Network (KAN), to achieve \\\"white-box\\\" modeling for\\nelectrical energy systems to enhance the interpretability. The most distinct\\nfeature of KAN lies in the learnable activation function together with the\\nsparse training and symbolification process. Consequently, KAN can express the\\nphysical process with concise and explicit mathematical formulas while\\nremaining the nonlinear-fitting capability of deep neural networks. Simulation\\nresults based on three electrical energy systems demonstrate the effectiveness\\nof KAN in the aspects of interpretability, accuracy, robustness and\\ngeneralization ability.\",\"PeriodicalId\":501034,\"journal\":{\"name\":\"arXiv - EE - Signal Processing\",\"volume\":\"106 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Signal Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.08044\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08044","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
深度学习方法因其便捷性和强大的模式识别能力,已被广泛用作电能系统的端到端建模策略。然而,由于其 "黑箱 "特性,深度学习方法在物理系统建模时一直被指责为可解释性差。在本文中,我们引入了一种新型的神经网络结构--Kolmogorov-Arnold 网络(KAN),以实现对电能系统的 "白箱 "建模,从而提高可解释性。KAN 的最大特点在于其可学习的激活函数以及稀疏的训练和符号化过程。因此,KAN 可以用简洁明了的数学公式表达物理过程,同时保持深度神经网络的非线性拟合能力。基于三个电能系统的仿真结果证明了 KAN 在可解释性、准确性、鲁棒性和泛化能力等方面的有效性。
A White-Box Deep-Learning Method for Electrical Energy System Modeling Based on Kolmogorov-Arnold Network
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 "black-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 "white-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.