Analysis of Fault Ride through the Improvement of PV Power Plant Based on Capacitive Bridge Fault Current Limiter Using Machine Learning

Abstract

Photovoltaic power plant (PVPP) has increased importance among renewable energy sources due to their ability to be connected more easily to a modern power grid. However, the reliability and stability operation of a grid-connected PVPP system is very important to ensure even during grid faults. In this study, a capacitive bridge fault current limiter (CBFCL) using a machine learning (ML) method is applied to enhance the fault ride-through (FRT) capability of a grid-connected PVPP system. Three different protection methods called DC chopper, CBFCL, and DC chopper + CBFCL are designed to prevent the harmful effects of overcurrent that occurs during grid faults to protect the grid-connected PVPP system. The ML algorithm can be trained on historical data to predict optimum control parameters based on real-time conditions such as normal and fault operations of the grid-connected PVPP system. An ensemble classification algorithm has the best results among the four classification algorithms in machine learning methods. The ensemble classification algorithm is separately implemented into the control systems of three protection strategies. Bagged Trees and Subspace KNN classifiers in ensemble classification methods have obtained an impressive accuracy of 98% in ML classification methods. The simulation results illustrate that the DC chopper + CBFCL based ensemble provides the best protection for the grid-connected PVPP system compared to other protection systems.