Load Prediction Model of Integrated Energy System Based on CNN-LSTM

Accurate load prediction is the premise of integrated energy system’s design, operation, scheduling and management. Most of the existing load forecasting models considered meteorological and date factors, but did not consider the correlation between electricity, cold and heat loads in system, which would affect the prediction accuracy of the model. In this paper, Copula theory was used to analyze the correlation between three kinds of loads in the system. From the analysis results, there was a strong correlation between the three loads. Based on the above analysis results, in order to improve the prediction accuracy of the model, this paper proposed a load prediction model of integrated energy system based on deep learning. Firstly, the model used Convolutional Neural Network (CNN) to extract the feature quantities related to the coupling characteristics of electric, cold and hot loads in the system. After converting the characteristic values into time series, these series were input into Long Short-Term Memory (LSTM) network for load prediction. Experimental results show that the prediction accuracy of CNN-LSTM combined model proposed in this paper is more accurate, which can provide reference for the load prediction of the system.