Multiple load short-term forecasting model of integrated energy system based on multiple LSTM networks

Abstract

Accurate short-term load forecasting of integrated energy system can optimize system operation and play an important role in improving system energy efficiency. In this paper, a multiple load short-term forecasting model of integrated energy system based on multiple LSTM networks is proposed. Firstly, the load influencing factors are divided into meteorological characteristic, delay characteristic and periodic characteristic, and the correlation is calculated based on Pearson coefficient. Secondly, a load forecasting model with multiple LSTM network coupling is established to explore the relationship between load and three characteristics, and excavate the complex coupling relationship among cooling, heating and power. The results show that the model has better prediction performance compared with other commonly used models.