Short-term Load Forecasting of Multi-Energy in Integrated Energy System Based on Multivariate Phase Space Reconstruction and Support Vector Regression Mode.

• The MPSR-SVR model is proposed to predict the electrical, heating, cooling and gas load of the IES. • The coupling characteristics among multiple loads of the IES are analysed. • The Pearson correlation coefficient is used to describe the correlation between multiple loads and environmental factors. • The C-C algorithm is used to reconstruct the phase space to fully explore the evolution law of time series. In order to alleviate the energy crisis and improve the energy utilization rate, the integrated energy system (IES) has become an important way of energy utilization. IES integrates electricity, natural gas, heating and cooling energy supply. Accurate energy load forecasting is essential, which has a significant impact on the economic scheduling and optimal operation of the IES. Herein, a combined model prediction method of multivariate phase space reconstruction (MPSR) and support vector regression (SVR) is proposed in this paper. First, a quantitative analysis of the coupling relationship between different integrated energy subsystems is conducted, and Pearson correlation analysis theory is used to analyse the historical time series of electrical, cooling, heat, gas loads and environmental factors one by one, then the input variables of the combined forecasting model are obtained. After that, the multivariate phase space is reconstructed by the C-C method, and the SVR model is used to predict electricity, cooling, heating and gas loads. Final, the model is validated by the actual data of the IES in Arizona State University, the results of three cases show the efficiency and high accuracy of the proposed forecasting method that considers the coupling relationship between multi-energy loads of IES. [ABSTRACT FROM AUTHOR]