Research on passive anti islanding protection method for distributed photovoltaic power generation based on deep learning

Distributed photovoltaics are mainly connected to low-voltage distribution networks of 35kV and below. When the power grid malfunctions, conventional distributed photovoltaics island protection methods have issues of island discrimination failure and unreliability, posing serious challenges to the safe and stable operation of the power grid. This paper proposes a new passive island recognition method based on deep learning to address the problem of complex and redundant feature selection and large blind spots in distributed photovoltaic island events. And compared with traditional anti islanding protection methods, simulation results show that this method can improve the accuracy of distributed power islanding detection and reduce detection blind spots.