Clustering and dynamic recognition based auto-reservoir neural network: A wait-and-see approach for short-term park power load forecasting

Jingyao Liu; Jiajia Chen; Guijin Yan; Wengang Chen; Bingyin Xu

doi:10.1016/j.isci.2023.107456

Clustering and dynamic recognition based auto-reservoir neural network: A wait-and-see approach for short-term park power load forecasting

iScience. 2023 Jul 22;26(8):107456. doi: 10.1016/j.isci.2023.107456. eCollection 2023 Aug 18.

Authors

Jingyao Liu¹, Jiajia Chen¹, Guijin Yan¹, Wengang Chen¹, Bingyin Xu¹

Affiliation

¹ School of Electrical and Electronic Engineering, Shandong University of Technology, Zibo 255000, China.

Abstract

This paper proposes a novel clustering and dynamic recognition-based auto-reservoir neural network (CDbARNN) for short-term load forecasting (STLF) of industrial park microgrids. In CDbARNN, the available load sets are first decomposed into several clusters via K-means clustering. Then, by extracting characteristic information of the load series input to CDbARNN and the load curves belonging to each cluster center, a dynamic recognition technology is developed to identify which cluster of the input load series belongs to. After that, the input load series and the load curves of the cluster to which it belongs constitute a short-term high-dimensional matrix entered into the reservoir of CDbARNN. Finally, reservoir node numbers of CDbARNN which are used to match different clusters are optimized. Numerical experiments conducted on STLF of an actual industrial park microgrid indicate the dominating performance of the proposed approach through several cases and comparisons with other well-known deep learning methods.

Keywords: Electrical engineering; Energy engineering; Energy systems; Engineering; Mechanical engineering.