A Day-Ahead Short-Term Load Forecasting Using M5P Machine Learning Algorithm along with Elitist Genetic Algorithm (EGA) and Random Forest-Based Hybrid Feature Selection

A hybrid feature selection (HFS) algorithm to obtain the optimal set attain forecast accuracy for short-term load forecasting (STLF) problems is proposed in this paper. The HFS employs an elitist genetic (EGA) and random forest method, which embedded online (FS). Using selected features, performance of forecaster was tested signify utility methodology. For this, a day-ahead STLF using M5P (a comprehensive approach regression tree concept) implemented with FS without (WoFS). (with WoFS) compared forecasters based on J48 Bagging. simulation carried out MATLAB WEKA software. Through analyzing forecasts Australian electricity markets, evaluation indicates that input by consistently outperforms larger sets.