Regional Electricity Consumption based on Least Squares Support Vector Machine

Least squares support vector machine is presented to predict regional electricity consumption in the paper. Least squares support vector machine is a kind of modified support vector machine, the method can use equality constraints for the error instead of inequality constraints which is used in the support vector machine. A certain regional electricity consumption data from 1999 to 2008 are applied to study the regional electricity consumption prediction performance of LSSVM. The least squares support vector machine prediction model of regional electricity consumption is created and the support vector machine model is applied to compare with the least squares support vector machine model. The comparison of relative error between least squares support vector machine prediction model and support vector machine prediction model is given. The experimental result indicates that the proposed model is accurate to predict the electricity consumption.