Comparision of different classifiers in fault detection in microgrid

Distributed Generation (DG) has gained more attention recently due to its flexibility and efficiency. In order to manage the DG efficiently, Micro Grid was introduced by some scholars because of its potential to increase the use of DG. A micro grid is a small power system consists of some different components e.g. distribution generators, energy storage devices, energy conversion devices, several loads and monitors. Any component in micro grid may go wrong thus lead to severe damage. This paper studies on fault detection of micro grid using several well-known classification methods such as Radial Basis Function Neural Network (RBFNN), Decision Tree (DT), KNN, and Naïve Bayes (NB). Those methods are compared in term of accuracy and time complexity experimentally in noisy-free and noisy environment.