Extreme Learning Machine Based Adaptive Distance Relaying Scheme for Static Synchronous Series Compensator Based Transmission Lines

摘要

This article presents an extreme learning machine based fast and accurate adaptive distance relaying scheme for transmission lines in the presence of a static synchronous series compensator. The ideal trip characteristics of the distance relay is greatly affected by pre-fault system conditions, ground fault resistance, and zero-sequence voltage. The proposed research develops an extreme learning machine based adaptive distance relaying scheme for two-terminal transmission networks with static synchronous series compensators when a single-line-to-ground fault situation is most likely to occur. The study includes an analytical approach, including a steady-state model of static synchronous series compensator with detailed simulation on MATLAB/Simulink (The Math Works, Natick, Massachusetts, USA) and open real-time simulation software with MATLAB (OPAL-RT) platform (OPAL-RT Technologies, Montreal, Quebec, Canada). The proposed extreme learning machine based adaptive distance relaying scheme is extensively validated on the two terminal transmission lines with static synchronous series compensators, and the performance is compared with the existing radial basis feed-forward neural network based adaptive distance relaying scheme. The results on simulation and real-time platform show significant improvements in the performance indices, such as speed, selectivity, and reliability of the digital relay.