The active power dispatching equivalent model of the virtual power plant (VPP) and the global dispatching optimization issue of the whole system integrated with the VPP equivalent model are studied in this paper. The active power dispatching equivalent model of the VPP is built as a deep learning model and trained by data sets of power output curve and the corresponding generation cost of the VPP. Global dispatching issue is formulated as a multi-objective optimization problem and solved by NSGAII algorithm. The deep learning model is verified by case study, and results show that the model is beneficial to both the VPP and the whole system. The proposed VPP equivalent model makes it possible to schedule VPP’s optimal power generation plan for the power dispatching center so as to maximize the generation revenue of the VPP and minimize the total generation cost of the whole system.

Virtual power plant, deep learning, dispatching equivalent model, global dispatching optimization, optimal power generation plan