Short-Term Power Load Forecasting Based on IWOA-Attention-BiLSTM

Abstract

Accurate power load forecasting can significantly improve the economic benefits of power systems. To improve the prediction accuracy, aiming at the complexity and volatility of power load, a forecasting model based on improved whale optimization algorithm (IWOA) optimized the bidirectional long short-term memory (BiLSTM) combined with attention mechanism (IWOA-Attention- BiLSTM) is proposed. The model comprehensively considers the influence of meteorological factors and date types, learns the bidirectional series features of power load data by BiLSTM, calculates the weights of the hidden layer state by the attention mechanism, and finds the hyperparameters of Attention-BiLSTM by IWOA, such as the learning rate, iteration times and batch size. The results show that compared with BP, LSTM and Seq2Seq, IWOA-Attention-BiLSTM has the highest prediction accuracy, and its MAPE, RMSE, MAE and R2 are 1.44 %, 128.83MW, 97.83MW and 0.9931 respectively, which are the best among all the prediction models. It is proved that IWOA-Attention- BiLSTM can effectively improve the prediction accuracy of short-term power load.