Research on the Performance of Different Load Forecasting Methods of Park Level

Load forecasting can not only improve energy utilization efficiency, but also improve the profitability in the electricity market. In this paper, load forecasting models based on recurrent neural network (RNN), long short-term memory network (LSTM) and convolutional neural network -long short-term memory network algorithms are established. According to it, the thermal, cold and electricity load forecasting of a hospital in 1 hour, 1 day and 1 week are carried out though above three models. The results show that under different time scale forecast, the forecasting method of convolutional neural network -long short-term memory network has the best accuracy.