An adaptive distance protection scheme for high varying fault resistances: Updated results

Abstract

The conventional distance protection scheme is usually affected by uncertainties associated with transmission line parameters and some uncontrolled parameters like fault resistances. By varying the fault resistances, errors are introduced in the fault distance estimation because the apparent impedance measured in the relay terminal is not proportional to the line length between the relay and fault location. This paper presents an adaptive protection scheme using Artificial Neural Network (ANN) to address the problem. The proposed scheme automatically adjusts its relay settings based on the fault resistance calculated using the acquired data obtained by the remote terminal unit RTU connected to field instruments at the local end. Communication between both ends is through fiber optic. A MATLAB based adaptive distance relaying scheme is developed using the ANN. PSCAD/EMTDC software is used to generate the current and voltage signals for specified lines which are used for subsequent ANN training and testing of the proposed algorithm. The proposed non-conventional adaptive scheme was validated with different high fault resistances that occurred on the 132 kV Aba - Owerri, and Aba-Umuahia transmission lines in Nigeria between January 2019 and June2019.The results show the ability of ANN to correctly detect, classify and localized fault under varying fault resistance.