Machine Learning Models for Electricity Consumption Forecasting: A Review
- 1 May 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
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.Keywords
This publication has 32 references indexed in Scilit:
- Short-term power forecasting system for photovoltaic plantsRenewable Energy, 2012
- Power load forecasting using support vector machine and ant colony optimizationExpert Systems with Applications, 2010
- Electricity consumption forecasting in Italy using linear regression modelsEnergy, 2009
- Forecasting electricity consumption in New Zealand using economic and demographic variablesEnergy, 2005
- Neural networks for short-term load forecasting: a review and evaluationIEEE Transactions on Power Systems, 2001
- Univariate modeling and forecasting of energy consumption: the case of electricity in LebanonEnergy, 2001
- Artificial neural networks for the prediction of the energy consumption of a passive solar buildingEnergy, 2000
- Applications of artificial neural networks in energy systemsEnergy Conversion and Management, 1999
- Electric load forecasting using an artificial neural networkIEEE Transactions on Power Systems, 1991
- A performance comparison of trained multilayer perceptrons and trained classification treesProceedings of the IEEE, 1990