Real-time estimation of ATC using PMU data and ANN

Abstract

An artificial neural network (ANN) architecture for real-time estimation of available transfer capability (ATC) has been reported in this study. The real-time data obtained from phasor measurement unit (PMU) is utilised to generate target output (ATC) using the pattern search optimisation-based method. The set of information provided as input to the pattern search-based ATC optimiser along with its output forms the input and target output for ANN training. The input information consists of active and reactive power injected along with voltage and current vectors measured at PMU buses. The ATC optimiser is functional as long as ANN is under training. Once the ANN is trained, it receives input set directly from PMU and produces ATC values. PMU emulation is employed for archiving the PMU data. The proposed method is tested on modified IEEE 24-bus, IEEE 30-bus, and IEEE 118-bus test system. The proposed method has also been implemented on real-time digital simulator.