Short Term Load Forecasting Model for Process Industry Based on Hybrid RNN-LSTM Algorithm: A Case Study of Textile Enterprises

According to the data of the National Bureau of statistics in 2020, the industrial load accounts for 67% of the total power load, accounting for a considerable proportion of the entire load. If the accurate prediction of short-term industrial load can be realized, it will provide necessary guarantee for the stability and security of the power grid. However, industrial load forecasting was more complex than other types of load forecasting. Then, a prediction model combining the recurrent neural network (RNN) with the industrial load mixing prediction model (RNN-LSTM) and the long short-term memory (LSTM) model was proposed. Compared with the LSTM model, the results show that RNN-LSTM was significantly improved for MAPE, MSE, and MAE.