Regression Models Comparison for Efficiency in Electricity Consumption in Ecuadorian Schools: A Case of Study

Abstract

Consumption forecast models with their proper billing allow establishing strategies to avoid overloads in systems and penalties for high consumption. This paper presents a comparison of multivariate data prediction models that allow detecting the final monthly cost of electricity consumption in relation to the different billing parameters. As relevant results, it was obtained that the models based on decision support machines have a better sensitivity when compared with different metrics that evaluate the prediction error with training set improved by backward elimination criteria.