To solve the problem that the high volatility of photovoltaic power leads to the lack of accuracy of the prediction model, a new short-term photovoltaic power prediction model is proposed in this paper, which integrates secretary bird optimization algorithm double decomposition (STSV), convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) neural network. Firstly, the Pearson correlation coefficient method is used to identify the key meteorological characteristics affecting the power of photovoltaic generation, and the secretary bird optimization algorithm is used to optimize the parameters of the time-varying filtering empirical mode decomposition. Subsequently, based on the complexity evaluation of sample entropy and the K-means clustering method, the decomposed modes are reconstructed into high-frequency, medium-frequency and low-frequency terms, and the high-frequency terms are subjected to variational mode decomposition to further reduce the volatility. Finally, the CNN-BiLSTM model is constructed to mine the internal relationship between photovoltaic power and meteorological factors, and the short-term photovoltaic power prediction is obtained by superimposing the prediction results of each component. Taking the actual data of a photovoltaic power station in Jiangsu Province as an example, the simulation results show that the root mean square error, mean absolute error and mean Absolute percentage error of the proposed model are reduced by 35.6%、32.3% and 29.6%, respectively, compared with other models, which significantly improves the prediction accuracy.
XINB A, SHANB G, LIQ H,et al .Rethinking of the “three elements of energy” toward carbon peak and carbon neutrality[J].Proceedings of the CSEE,2022,42(9): 3117-3126.(in Chinese)
ZHANGY M, SUNP K, JIX Q,et al .Dynamic economic dispatch for integrated energy system based on parallel multi-dimensional approximate dynamic programming[J].Automation of Electric Power Systems,2023,47(4): 60-68.(in Chinese)
WUC H, DONGA L, LIZ H, et al. Photovoltaic power prediction based on graph similarity day and PSO-XGBoost[J]. High Voltage Engineering,2022,48(8):3250-3259.(in Chinese)
[7]
KRISHNA RAYIV, MISHRAS P, NAIKJ,et al .Adaptive VMD based optimized deep learning mixed kernel ELM autoencoder for single and multistep wind power forecasting[J].Energy,2022,244:122585.
QIANY S, KONGY T, HUANGC. Review of power load forecasting[J]. Sichuan Electric Power Technology,2023,46(4): 37-43.(in Chinese)
[12]
高贵刚. 新能源风光发电预测技术进展综述[J]. 电工技术,2022(20): 49-52.
[13]
GAOG G .Review of the progress in forecasting technology for new energy wind and solar power generation[J]. Electric Engineering,2022(20): 49-52.(in Chinese)
YANGJ, CHANGX J, YAOS,et al. Day-ahead photovoltaic power forecasting based on WT-CNN-BiLSTM model[J]. Southern Power System Technology, 2024,18(8):61-69.(in Chinese)
LONGX H, QINJ Y, ZHANGQ L,et al .Short-term photovoltaic power prediction study based on similar day clustering and modal decomposition[J].Power System Technology,2024,48(7):2948-2957.(in Chinese)
LIW Z, LIM, LIUJ,et al .Ultra-short-term photovoltaic power prediction based on TVF-EMD-ELM[J].Electrical Engineering Materials, 2023(6): 44-48.(in Chinese)
BIG H, ZHAOX, CHENC P, et al. Ultra-short-term prediction of photovoltaic power generation based on multi-channel input and PCNN-BiLSTM[J]. Power System Technology, 2022, 46(9): 3463-3476.(in Chinese)
YANGJ X, ZHANGS, LIUJ C,et al .Short-term photovoltaic power prediction based on variational mode decomposition and long shortterm memory with dual-stage attention mechanism[J].Automation of Electric Power Systems,2021,45(3):174-182.(in Chinese)
[26]
FUY F, LIUD, CHENJ D,et al .Secretary bird optimization algorithm:a new metaheuristic for solving global optimization problems[J]. Artificial Intelligence Review, 2024, 57(5): 123.
WANGR, ZHANGL T, LUJ .Short term photovoltaic power prediction based on new similar day selection and VMD-NGO-BiGRU[J]. Journal of Hunan University (Natural Sciences),2024, 51(2): 68-80.(in Chinese)
JIX Q, ZHAOG H, YEP F, et al. Short-term PV forecasting method based on the QMD-HBiGRU model[J]. High Voltage Engineering, 2024, 50(9): 3850-3859.(in Chinese)