Title: A method of selecting characteristics based on P_KPCA for new power system operation mode

Authors: Xiaoli Guo; Qingyu Shan; Zhenming Zhang; Hao Jiang

Addresses: School of Computer Science, Northeast Electric Power University, Jilin, China ' School of Computer Science, Northeast Electric Power University, Jilin, China ' School of Electrical Engineering, Northeast Electric Power University, Jilin, China ' School of Civil Engineering and Architecture, Northeast Electric Power University, Jilin, China

Abstract: With the increasing role of renewable energy in the power system, the characteristic variables of the new power system operation mode are made to develop towards high dimensionality and diversification. As a result, the applicability and accuracy of the traditional feature variable screening methods are insufficient. For this reason, a method of selecting characteristics based on P_KPCA for a new power system operation mode is proposed. Firstly, to quantify the correlation between the various operating variables, a correlation quantification method based on the Pearson coefficient of the characteristic variables of the operating mode is designed. Then, the feature vector dimension is reduced to reduce the impact on the extraction accuracy of the operating mode, a screening model for strongly correlated characteristic variables of the operation mode based on P_KPCA is constructed. Finally, based on more than 8000 power grid operation sections, experimental verification is carried out to verify the accuracy and rationality of the method in this paper.

Keywords: power operation data; new power system; feature dimension reduction; kernel principal component analysis; dimension reduction.

DOI: 10.1504/IJWMC.2024.139771

International Journal of Wireless and Mobile Computing, 2024 Vol.27 No.1, pp.92 - 102

Received: 14 Aug 2023
Accepted: 18 Oct 2023
Published online: 05 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article