• load forecasting;
  • load profiling;
  • support vector regression;
  • simulated annealing;
  • feature selection


The article proposes a methodology to forecast the electric load for the 24 h of the following day based on support vector regression. The study considers 24 distinct models, one for each predicted hour, where each individual model is treated independently. Its objective is to find the optimal combination of support vector machine parameters that could generalize low forecasting errors, using simulated annealing as a metaheuristic. The adopted methodology is compared to concurrent methods based on neural networks when applied to a simulated load diagram (to illustrate a distribution feeder supplying a sample of 740 consumers). The results have proven its effectiveness with mean absolute percentage errors being less than 5% for testing samples. The study also focuses on evaluating the potential benefits of adopting load profiling information as input in support vector regression, giving a consistent proof of its importance. Copyright © 2013 John Wiley & Sons, Ltd.