Open AccessFault identification in a grid connected solar PV system using Back propagation Neural Network
Author(s) -
M. Mano Raja Paul,
R. Kannan,
M. Leeban Moses,
A. Bhuvanesh
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1084/1/012109
Subject(s) - photovoltaic system , maximum power point tracking , renewable energy , fault (geology) , grid connected photovoltaic power system , engineering , electric power system , automotive engineering , computer science , electrical engineering , power (physics) , inverter , physics , voltage , quantum mechanics , seismology , geology
Albeit the government buoy up the penetration of renewable energy sources (RES) particularly solar photovoltaic (PV) system, the dependency on fossil fuels is still growing. The power generation using solar PV system may enhance when the enactment of solar PV system is improved. The faults occurred in the system is an important performance degradation factor. Incessant studies have been performed to identify and mitigate the faults. Currently, several smart techniques are utilized to identify the faults rapidly. In this study, Back Propagation Neural Network (BPNN) has been implemented to identify the faults. The output power get degraded when the faults happened in source side, Maximum Power Point Tracking (MPPT), DC-DC converter, rectifier and grid. The investigations has performed on 100 kW solar PV system using Matlab. The outcomes imply that the proposed method has detected the faults quickly, economically and effectively.