Energy Consumption Forecasting in Process Industry Using Support Vector Machines and Particle Swarm Optimization

摘要

In this paper, Support Vector Machines (SVMs) are applied in predicting energy consumption in the first phase of oil refining at a particular oil refinery. During cross-validation process of the SVM training Particle Swarm Optimization (PSO) algorithm was utilized in selection of free SVM parameters, widths of radial basis functions to be exact. Incorporation of PSO into SVM training process has greatly enhanced the quality of prediction.