Diagnosis of PV module based on neural network using performance indices

Nadjib Mekhaznia, Riad Khenfer


Solar energy is an inexhaustible and clean renewable energy. Its exploitation through photovoltaic panels is clearly increasing in the world as ecologic energy. But like the conventional power grids, this new green energy could be affected by several defects that could reduce its performance, cause negative economic and safety impacts. These faults are multiple and of different natures. their consequences are based on their dangerousness. They can cause malfunction, power reduction and even total shutdown of the PV. The goal of this contribution is to implement an artificial method based on the ANN to diagnose the faults of the solar modules and to study the interest of the performance indices for the interpretation of the results of the diagnosis of the PV module. The results obtained are widely commented by different performance indices of confusion matrix and ROC curves. The neural network-based diagnostic system has a high accuracy and training was efficient because the curves of the cases are in the vicinity of unity i.e., a perfect classification.


Confusion matrix; Diagnosis; Neural network; Photovoltaic system; ROC curves

Full Text:


DOI: http://doi.org/10.11591/ijpeds.v14.i4.pp2347-2353


  • There are currently no refbacks.

Copyright (c) 2023 Nadjib Mekhaznia

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.