期刊
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
卷 9, 期 1, 页码 99-110出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JAS.2021.1004284
关键词
Artificial neuron networks (ANNs); dendrite neuron network; differential evolution (DE); scale-free network
资金
- National Natural Science Foundation of China [62073173, 61833011]
- Natural Science Foundation of Jiangsu Province, China [BK20191376]
- Nanjing University of Posts and Telecommunications [NY220193, NY220145]
This research introduces a differential evolution algorithm based on a dynamic scale-free network to address the limitations of traditional artificial neuron networks. Experimental results on benchmark datasets and a photovoltaic power forecasting problem demonstrate that the proposed algorithm outperforms other methods.
Some recent research reports that a dendritic neuron model (DNM) can achieve better performance than traditional artificial neuron networks (ANNs) on classification, prediction, and other problems when its parameters are well-tuned by a learning algorithm. However, the back-propagation algorithm (BP), as a mostly used learning algorithm, intrinsically suffers from defects of slow convergence and easily dropping into local minima. Therefore, more and more research adopts non-BP learning algorithms to train ANNs. In this paper, a dynamic scale-free network-based differential evolution (DSNDE) is developed by considering the demands of convergent speed and the ability to jump out of local minima. The performance of a DSNDE trained DNM is tested on 14 benchmark datasets and a photovoltaic power forecasting problem. Nine meta-heuristic algorithms are applied into comparison, including the champion of the 2017 IEEE Congress on Evolutionary Computation (CEC2017) benchmark competition effective butterfly optimizer with covariance matrix adapted retreat phase (EBOwithCMAR). The experimental results reveal that DSNDE achieves better performance than its peers.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据