基于SVR的多变量电力消费预测

Prediction for Multivariable Electricity Consumption Based on SVR

电力消费受多种因素的影响,揭示因素与电力消费的关系是当前电力消费研究的一个重要内容.应用支持向量回归机模型,利用年电力消费、人均国内生产总值、重工业比重以及电能效率的数据,分别对电力消费进行双变量和多变量的支持向量回归机预测.实验对比分析两种方式下预测值与真实值差异情况,说明了多变量方式下支持向量回归机的预测值与真实值更一致.

Electricity consumption is affected by many factors, and the relationship between the factors and the electricity consumption has become one of important study contents of the electricity consumption. In this paper, the support vector regression model is used to predict the electricity consumption by two ways of bivariate and multivariate regression separately. Adopted data includes the electricity consumption per year, the per capita gross domestic product, the proportion of heavy industry and the energy efficiency. The difference between predicted values and actual values, which are obtained in two ways, is compared and analyzed by experiments. The experimental results show that the predicted value and the actual value obtained in the way of multivariate regression are more consistent than the other way.