A Novel Bi-Directional Grid Inverter Control Based on Virtual Impedance Using Neural Network for Dynamics Improvement in Microgrids

In microgrids, the voltage source inverters often use the droop control technique along with voltage and inner current control loops to achieve a reliable electrical supply. Because of the unmatched line impedance, the standard droop control technique makes it difficult to uniformly distribute power and limit circulating flow across parallel connections, especially in highly nonlinear systems. The purpose of this research is to introduce a neural network-based virtual impedance integrated with a bi-directional grid inverter control technique that improves stability during the dynamic operation of microgrids. In order to track demand and reference power accurately with less deviation and better stability under various operating scenarios, the suggested technique employs the Feed-Forward Neural Network (FFNN) to learn the nonlinear model during the transient state of the inverter. It consists of adding compensation voltages without any further tuning procedure. The proposed FFNN controller's extensive transient stability analysis, power tracking, and operational performance are assessed in various dynamic scenarios using the power hardware-in-the-loop (PHIL) technique. In addition, the robustness and performance of the proposed approach are validated on the IEEE 33-bus standard distribution system. All findings are compared to the tried-and-true conventional technique to demonstrate its efficacy.