A Data-Mechanism Joint Driven Based Multi-Energy Flow Calculation Method for Electricity-Heat Interconnected System

With the rapid development of integrated energy system (IES), the combine operation of heterogeneous energy networks becomes richer and richer, and the nonlinear characteristics of the multi-energy flow (MEF) model become more and more significant, which poses a challenge to the analysis and optimization of system operation. In this paper, a joint driven MEF modeling method based on electricity-heat interconnected system is proposed, which utilizes a deep learning method to mine the internal relationship of MEF historical data and effectively avoids the stability problem caused by iterative. On this basis, the fusion mechanism-driven module is used as a buffer zone for the nonlinear regression process of MEF to reduce the error stacking. This model can achieve the organic unification of calculation accuracy and timeliness to a certain extent. Finally, different scales of electricity-heat interconnection systems are selected for example analysis to verify the accuracy and implementation of the proposed method.