High-Speed Railway Load Forecasting Method Based on QPSO-LSTM
Junpeng Xu, Zizhuo Wang · 2024
Aiming at the difficulty of high-speed railway load forecasting, this paper proposes a forecasting model based on QPSO-LSTM. The model combines the long and short-term memory capabilities of the LSTM network and the global search capability of the QPSO algorithm, performs deep learning and parameter optimization on the high-speed railway load sequence, and improves the forecasting accuracy and stability. Taking a certain high-speed railway line as an example, this paper uses real data for experimental verification and compares it with other commonly used models. The results show that the method proposed in this paper is superior to other models and can effectively reflect the changing trend and fluctuation characteristics of high-speed railway load.