Machine Learning Models for Electricity Consumption Forecasting: A Review

摘要

The prediction of energy consumption is a task that allows energy supply companies to adapt to certain behaviors. Among these activities that companies can perform is to know the behavior of their customers to adapt their rates to consumption or know the intervals in which it will produce a greater demand for energy and have planned the adaptation of supply chains. In this sense, it is necessary to carry out an evaluation of methods that allow forecasting future energy consumption based on the consumption history and other variables of the users themselves. In this article, a review of the main machine learning models that allow predicting energy consumption using a one-year data set of a shoe store was made. The review made allowed to observe that for the data set using the Linear Regression and Support Vector Regression has obtained a success of 85.7% being the best results provided.