Optimizing SVR Based on Grey Wolf Algorithm to Predict the Enterprise's Maximum Demand
With the structural reform of the power supply side,fast and accurate forecasting of power demand will help enterprises to rationally arrange production plans,reduce the cost of electricity consumption,and reduce the pressure on the power grid side.Significance.Based on support vector regression(SVR),this paper analyzes the prediction model of the enterprise's maximum demand,performs correlation analysis and dimension reduction processing on the input features of the model,and uses the grey wolf optimizer(GWO)to optimize the model.Internal hyperparameters to achieve better prediction performance.Finally,combined with real data,the prediction performance of BPNN,SVR,GWO-SVR three methods is compared through Matlab simulation,and the effectiveness and accuracy of the proposed method are verified.
support vector machinegrey wolf algorithmcorrelation analysis
NETL
NSTL
万方数据
