Islanding detection of Distributed Generation using Random Forest technique

In this article, an islanding detection scheme for distribution network having high penetration of Distributed Generations (DGs) is proposed. The proposed scheme is based on classification of islanding and non-islanding events using Random Forest (RF) classifier. The RF classifier utilizes sequence components of voltages which are obtained by acquiring voltage samples of all the phases from point of common coupling (PCC) of the targeted DG. Validity of the proposed scheme has been evaluated on large number of islanding/non-islanding cases which are generated by modeling standard IEEE 34-bus system in Real time digital simulator (RTDS) software. The simulation results indicate that the proposed scheme is capable to provide effective discrimination between islanding situation and non-islanding events. Moreover, it also gives satisfactorily results during perfect power balance situation. In addition, it provides better stability in case of non-islanding events and hence, avoids nuisance tripping.