Transfer Learning based Impedance Identification of Voltage Source Converters

The black-box impedance of the voltage source converters (VSCs) can be directly identified at the converter terminal without access to its internal control details, which greatly facilitates the converter-grid interactions. However, since the limited impedance data amount in practical industrial applications, the existing impedance identification methods cannot accurately capture characteristics of the impedance model at various operating scenarios, which is the indicators of the VSCs system stability at the changing profiles of renewables and loads. In this paper, a transfer learning based impedance identification is proposed to fill this research gap. This method can significantly reduce the required data amount used in impedance identification so that the black-box impedance-based stability method could be applied for the practical industrial application. The comparison results confirm the accuracy of the impedance model obtained by this transfer learning based impedance identification method.