An Improvement In Load Forecasting Model Using Parametric Tuned Support Vector Machine (SVM) Kernel Based Functions

Short term load forecasting (STLF) has gained huge interest among researchers because of its applications in economics, reliability, unit commitment (UC), economic dispatch (ED) and hydro-thermal coordination (HTC) of power systems. The aim of this study is to find an accurate algorithm as it is very important for the prediction of accurate load forecast. Support Vector Machine Regression Model (SVM-R) using different kernels i-e linear, polynomial and gaussian has been used and each kernel function effectiveness and its performance has been examined on real time series using ISO-New England utility data. LibSVM using R language is utilized in this research to employ SVM-R Model. Artificial Neural Network (ANN) is utilized to compare and check the effectiveness of proposed model and its performance by considering least Mean Absolute Percentage Error.