QPSO-LSTM Based Electricity Sales Forecasting Model

Accurate power sales forecasting can help optimize the power supply structure, improve the reliability of power supply, and ensure the safe operation of the power system. Meanwhile, with the rapid development of artificial intelligence, and the research involves its research results are increasingly applied in the theory and practice of power system research. To increase the precision of electricity sales forecast, the article discusses an algorithm based on QPSO algorithm to optimize the LSTM neural network, which is aimed at combining the basic principles of LSTM neural network and QPSO algorithm, and optimizing the hyper-parameters of the LSTM and its network topology by using QPSO algorithm. Thus, a QPSO-LSTM power sales forecast model is built. The simulation results show that the prediction precision of the QPSO-LSTM model is better than that of LSTM and PSO-LSTM.