Data-Driven Hybrid Equivalent Dynamic Modeling of Multiple Photovoltaic Power Stations Based on Ensemble Gated Recurrent Unit

With the increasing penetration of the photovoltaic (PV) in the distributed grid network, the dynamic response analysis of the system becomes more and more complex and costs lots of computational time in the simulation. To cut down the computational resources while guaranteeing the accuracy, this paper proposes a data-driven hybrid equivalent model for the dynamic response process of the multiple PV power stations. The data-driven hybrid equivalent model contains the simple equivalent model and data-driven error correction model. In the equivalent model, the distributed PV power stations in the same branch are equivalent to one power station model based on the parameter equivalence and feeder equivalence. The data-driven error correction model tracks and corrects the difference of dynamic response between the equivalent model and precise model. The ensemble Gated Recurrent Unit (GRU) model based on the bagging ensemble structure utilizes the simple equivalent dynamic response as input to learn the dynamic response errors. The simulation results validate the super-performance of the proposed model both in the response speed and accuracy.