Research on a Photovoltaic Power Prediction Model Based on VMD-QPSO-LSTM

Photovoltaic (PV) power forecasting plays a critical role in power grid dispatching and the integration of renewable energy sources. To improve the accuracy of PV power prediction, this paper proposes a hybrid forecasting model based on Variational Mode Decomposition (VMD), Quantum-behaved Particle Swarm Optimization (QPSO), and Long Short-Term Memory (LSTM) neural networks. First, the VMD method is employed to decompose the PV power time series into a set of Intrinsic Mode Functions (IMFs), aiming to reduce the non-stationarity and complexity of the original data. Then, the QPSO algorithm is introduced to optimize the key hyperparameters of the LSTM network globally, thereby enhancing the adaptability and generalization capability of the model. Finally, the processed subsequences are fed into the LSTM network for training and forecasting, and the outputs are aggregated to obtain the final PV power prediction. To verify the accuracy of the proposed method, actual PV power data from Chicheng County, Zhangjiakou, are used for prediction analysis. The results are compared with those of traditional LSTM and VMD-LSTM models. The comparison of forecasting metrics demonstrates that the VMD-QPSO-LSTM model achieves higher prediction accuracy and better fitting performance.