To address the limitations of traditional photovoltaic (PV) power prediction models in terms of forecasting accuracy and generalization capability
this paper designs and implements a prediction model that couples PCC
LSTM and XGBoost algorithms. Firstly
PCC is utilized to filter multi-dimensional features that influence PV power generation
thus constructing an optimized input feature set. Secondly
LSTM network is employed to model the long-term dependencies within the time series data
providing an initial power prediction. Concurrently
the XGBoost algorithm is introduced to model and predict the non-linear features of PV power generation. Finally
this paper lies in enhancing prediction accuracy and generalization capabilities by integrating the prediction results from LSTM and XGBoost models. Experimental results demonstrate that the proposed fusion model exhibits higher accuracy and stability in mid-and long-term PV power rolling forecasts
significantly outperforming traditional methods. Therefore
the proposed PCC-LSTM-XGBoost model offers a novel technical approach for accurate PV power prediction
making it particularly suitable for forecasting PV station power under various climatic conditions.
关键词
Keywords
references
DHAKED D K, DADHICH S, BIRLA D.Power output forecasting of solar photovoltaic plant using LSTM[J]. Green energy and intelligent transportation, 2023, 2(5): 100113.
NI Q, ZHUANG S X, SHENG H M, et al.An optimized prediction intervals approach for short term PV power forecasting[J]. Energies, 2017, 10(10): 1669.
ALARAJ M, ALSAIDAN I, KUMAR A, et al.Advanced intelligent approach for solar PV power forecasting using meteorological parameters for Qassim region, Saudi Arabia[J]. Sustainability, 2023, 15(12): 1-16.
TAVARES I, MANFREDINI R, ALMEIDA J, et al.Comparison of PV power generation forecasting in a residential building using ANN and DNN[J]. IFAC-PapersOnLine, 2022, 55(9): 291-296.