Determination of generators' contributions to, loads in pool based power system using Least Squares Support Vector Machine

Abstract

This paper attempts to allocate the generators' contributions to loads in pool based power system by incorporating the Least Squares Support Vector Machine (LS-SVM). The idea is to use supervised learning approach to train the LS-SVM. The technique that uses proportional tree method (PTM) which is applying the convention of proportional sharing principle is utilized as a teacher. Based on converged load flow and followed by PTM for power tracing procedure, the description of inputs and outputs of the training data for the LS-SVM are created. The LS-SVM will learn to identify which generators are supplying to which loads. The proposed technique is demonstrated using IEEE 14-bus system to illustrate the effectiveness of the LS-SVM technique compared to that of the PTM. The comparison result with Artificial Neural Network (ANN) technique is also will be discussed.