Comparative Study of Short-term Electric Load Forecasting: Case Study EVNHCMC

Abstract

Short-term load forecasting (STLF) plays an important role in building business strategies and ensuring reliability and safe operation of any electric power system. There are many different methods used for short-term forecasting, including regression models, time series, neural networks, expert systems, fuzzy logic, machine learning, and statistical algorithms. There are always debates about which algorithms are the best for electric load forecasting. In this paper, we compared the SVR (Support Vector Regression), NN (Neural Network) and RFR (Random Forest Regression) algorithms, based on the dataset of EVNHCMC to find out a suitable STLF for the dataset.