Short-Term Interval Forecasting of Photovoltaic Power Based on CEEMDAN-GSA-LSTM and SVR

被引：0

作者：

Li F. ^{[1
]}

Sun L. ^{[1
]}

Wang Y. ^{[2
]}

Qu A. ^{[3
]}

Mei N. ^{[4
]}

Zhao J. ^{[1
]}

机构：

[1] College of Electric Power Engineering, Shanghai University of Electric Power, Shanghai

[2] Laboratory of Low Frequency Electromagnetic Communication Technology, The 722 Research Institute, CSSC, Wuhan

[3] Mathematics and Science College, Shanghai Normal University, Shanghai

[4] State Grid Economic and Technological Research Institute Co., Ltd., Beijing

来源：

Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University | 2024年 / 58卷 / 06期

关键词：

complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN); gravitational search algorithm (GSA); interval prediction; Johnson transformation; long short-term memory (LSTM); photovoltaic power prediction; support vector regression (SVR);

D O I：

10.16183/j.cnki.jsjtu.2022.511

中图分类号：

学科分类号：

摘要：

Aimed at the intermittency and fluctuation of photovoltaic output power, a short-term interval prediction model of photovoltaic power is proposed. First, the model uses the complete ensemble empirical mode decomposition of adaptive noise (CEEMDAN) to decompose the historical photovoltaic output data into different components and define them as time-series components and random components according to their correlation with time-series features such as declination and time angles. Then, the long short-term memory (LSTM) neural network and the support vector regression (SVR) model optimized by the gravitational search algorithm (GSA) are used to predict the time series components and the random components respectively, and the prediction results of the time series components and the random components are superimposed to obtain the point prediction result. After the error is subjected to Johnson transformation and normal distribution modeling, the photovoltaic power interval prediction result is obtained. Finally, the effectiveness of the method is verified by an example. The comparison of the proposed model with other existing prediction models under different weather conditions suggests that the proposed model has a higher accuracy and a better robustness, which can provide precise confidence intervals based on point prediction values. © 2024 Shanghai Jiaotong University. All rights reserved.

引用

页码：806 / 818

页数：12

共 27 条

[1] The implementation plan for promoting the high-quality development of new energy in a new era
[2] ZHANG Yunqin, CHENG Qize, JIANG Wenjie, Photovoltaic power prediction model based on EMD-PCA-LSTM, Acta Energiae Solaris Sinica, 42, 9, pp. 62-69, (2021)
[3] YE Lin, MA Mingshun, JIN Jingxin, Et al., Factor analysis-extreme learning machine aggregation method considering correlation of wind power and photovoltaic power, Automation of Electric Power Systems, 45, 23, pp. 31-40, (2021)
[4] Lljiaming, Al Xiaomeng, WEN Jinyu, elal, Quantitative analysis of probability distribution for duration time characteristic of photovoltaic power, Automation of Electric Power Systems, 41, 6, pp. 30-36, (2017)
[5] LI Fen, ZHOU Erchang, SUN Gaiping, Et al., A novel weather classification method and its application in photovoltaic power prediction, Journal of Shanghai Jiao Tong University, 55, 12, pp. 1510-1519, (2021)
[6] TANG Yajie, LIN Da, NI Chouwei, Et al., XGBoost based BiTayer collaborative real-time calibration for ultra-short-term photovoltaic prediction, Automation of Electric Power Systems, 45, 7, pp. 18-27, (2021)
[7] AGGA A, ABBOU A, LABBADI M, Et al., CNN-LSTM
[8] An efficient hybrid deep learning architecture for predicting short-term photovoltaic power produc-tion, Electric Power Systems Research, 208, (2022)
[9] WAN Can, GUI Wenkang, SONG Yonghua, Probabilistic forecasting for power systems with renewable energy sources: Basic concepts and mathematical principles[J], Proceedings of the CSEE, 41, 19, pp. 6493-6509, (2021)
[10] LI Min, LIN Xiangning, ZHANG Zheyuan, Et al., Interval prediction algorithm for ultra-short-term photovoltaic output and its Application, Automation of Electric Power Systems, 43, 3, pp. 10-16, (2019)

← 1 2 3 →