Data-Driven Modeling Method of Multi-Operation Impedance Identification for DFIG Based on Transfer Learning Theory

The multi-operation impedance identification of the doubly fed induction generator (DFIG) is essential to analyze the DFIG-grid interaction stability considering various operating conditions. However, the existing identification methods require a substantial amount of measurement data and lack effective transferability to other DFIGs with different parameters or control structures. To address this issue, this paper proposes a data-driven modeling method of multi-operation impedance identification for DFIG based on transfer learning theory. The multi-operation impedance model is established based on the common features of the DFIGs derived from theoretical formulas. Then, transfer learning theory is adopted to enhance flexibility of the model, allowing for appropriate architectural adjustments to adapt for different DFIGs. Finally, a serial update method for measured datasets and the identification model is developed. The proposed method can significantly reduce the required data amount and improve transferability of the identification model. The experiments based on control-hardware-in-loop (CHIL) are conducted to verify the effectiveness of the proposed method.