Adaptive overcurrent protection scheme coordination in presence of distributed generation using radial basis neural network
Uma Uzubi Uma, Daniel Nmadu, Nnaemeka Sunday Ugwuanyi, Ogah E. Ogah, Ngozi Clara Eli-Chukwu, Marcellinus I. Eheduru, A.O. Ekwue
Abstract
Abstract The operational performance of conventional overcurrent protection relay coordination connected to a distribution network is adversely affected by the penetration of distributed generators (DG) at different buses in the network. To address this problem, this paper proposes a novel adaptive protection coordination scheme using a radial basis function neural network (RBFNN), which automatically adjusts the overcurrent relay settings, i.e., time setting multiplier (TSM) and plug setting multiplier (PSM) based on the penetration of DGs. Short circuit currents and voltages measured at different buses are acquired using the remote terminal units (RTU) connected to different buses within the terminal network. Communication between the various remotes and local end station RTUs is through hybrid communication systems of fiber optic and power line communication system modules. The new adaptive overcurrent protection scheme is applied to the IEEE 33-bus distribution network with and without DGs, for single and multi-DG penetration using both the ETAP and MATLAB software. The simulation results show the proposed scheme significantly improves the protection coordination.