Impedance Dataset Optimization Method for Data-Driven Modeling of Renewable Power Generation Equipment Considering Multi-Operation Conditions

The data-driven approaches have been extensively developed for multi-operation impedance modeling of the renewable power generation equipment (RPGE). However, due to the black box of RPGE, the dataset used for establishing impedance model lacks theoretical guidance for data generation, which reduces data quality and results in a large amount of data redundancy. To address this issue, this paper proposes an impedance dataset optimization method for data-driven modeling of RPGE considering multi-operation conditions. The objective is to improve the data quality of the impedance dataset, thereby reflecting the overall impedance characteristics with a reduced data amount. Firstly, the impact of operation conditions on impedance is evaluated to optimize the selection of operating points. Secondly, at each operating point, the frequency distribution is designed to reveal the impedance characteristics with fewer measurement points. Finally, a serial update method for measured datasets and the multi-operation impedance model is developed to further refine the dataset. The experiments based on control-hardware-in-loop (CHIL) are conducted to verify the effectiveness of the proposed method.