Prediction method of short‑term PV output power based on PCA‑VMD‑MVO‑SVM

Authors

Gang ZOU, College of Electrical and Information Engineering, Changsha University of Science & Technology, Changsha 410114, China
Bin ZHAO, College of Electrical and Information Engineering, Changsha University of Science & Technology, Changsha 410114, China; State Key Laboratory of Disaster Prevention and Reduction for Power Grid, Changsha 410114, ChinaFollow
Qiang LUO, College of Electrical and Information Engineering, Changsha University of Science & Technology, Changsha 410114, China; Yongzhou Power Supply Company, State Grid Hunan Electric Power Co., Ltd., Yongzhou 425000, China
Gao LIANG, Hunan Red Solar New Energy Science and Technology Co., Ltd., Changsha 410111, China
Li WANG, College of Electrical and Information Engineering, Changsha University of Science & Technology, Changsha 410114, China; State Key Laboratory of Disaster Prevention and Reduction for Power Grid, Changsha 410114, China

Keywords

photovoltaic power generation; short-term power prediction; principal component analysis; variational mode decomposition; multi-verse algorithm; support vector machine

Abstract

To enhance the accuracy and reliability of short-term photovoltaic (PV) output power forecasting, a hybrid model is proposed, which integrates principal component analysis (PCA), variational mode decomposition (VMD), and multi-verse optimizer (MVO) to optimize a support vector machine (SVM) for PV output power prediction. Initially, PCA's data analysis capabilities and VMD's data decomposition performance are leveraged to reduce the dimensionality and decompose the multidimensional training data. Subsequently, the extracted dataset is fed into an SVM prediction model optimized by the MVO algorithm to obtain PV output power forecast components for different intrinsic modes. Finally, the results of these forecast components are aggregated. The research findings indicate that the proposed model achieves mean absolute percentage errors (MAPEs) of 0.7453%, 0.5105%, and 1.0156% for sunny, partly cloudy, and rainy days, respectively. Taking partly cloudy weather as an example, the MAPE of the proposed model is reduced by 3.8207%, 2.9173%, and 1.8438% compared to the MVO-SVM, VMD-MVO-SVM, and PCA-MVO-SVM models, respectively.

DOI

10.19781/j.issn.1673-9140.2024.05.017

First Page

163

Last Page

171

Recommended Citation

ZOU, Gang; ZHAO, Bin; LUO, Qiang; LIANG, Gao; and WANG, Li (2024) "Prediction method of short‑term PV output power based on PCA‑VMD‑MVO‑SVM," Journal of Electric Power Science and Technology: Vol. 39: Iss. 5, Article 17.
DOI: 10.19781/j.issn.1673-9140.2024.05.017
Available at: https://jepst.researchcommons.org/journal/vol39/iss5/17