Rreseach on Optimal Scheduling Strategy of CHP Microgrid Based on Combined Prediction Model

In the face of the impact of renewable energy uncertainty, traditional scheduling methods will be difficult to ensure the stable operation of the system. Aiming at the above problems, an optimal scheduling strategy of combined heat and power-microgrid (CHP) microgrid based on combination forecasting model is proposed. Firstly, a combined prediction model based on neural network and bidirectional long short-term memory network is constructed to provide effective prediction data for optimal scheduling. Secondly, the two-stage power prediction of wind power and photovoltaic is carried out by using the combined prediction model. Finally, a day-ahead and intraday two-stage optimal scheduling model is established, and the day-ahead scheduling plan is solved with the goal of minimizing the total operating cost of the system. The intra-day scheduling plan adopts the rolling optimal scheduling strategy of model predictive control to realize the minimum adjustment of the output of each unit. The example verifies that the proposed method can effectively improve the economy and stability of the system operation.