A novel modeling method of multi-energy system based on LSTM algorithm

The development of Energy Internet has improved the efficiency of energy utilization and promoted the sustainable development of power and energy systems. The multi-energy system modeling considering the dynamic process of transmission line is one of the key research point of Energy Internet operation control. Through the energy circuit theory, the lumped parameter model of natural gas pipeline is built and the dynamic characteristic parameters under the control instruction are extracted. Combined with the dynamic characteristic parameters, the Long Short-Term Memory (LSTM) neural network was designed to fit the natural gas pipeline dynamic process into discrete linear time-varying (LTV) equations. Combined with the equations, an energy hub method is used to build the control model of industrial park with multi-energy distribution system. Using the rolling optimal control strategy given in this paper, the model is solved by the Matlab-Yalmip solver and the rolling control instructions of each energy conversion unit are obtained. Finally, the case study demonstrates that the LSTM neural network-based modeling method presented in this paper can accurately fit the dynamic process of natural gas pipeline system. And the rolling control model of the multi-energy system can improves the efficiency of energy utilization, explicit the transmission line status constraints during the optimization control process and improves the reliability of the multi-energy system operation.