Short-term Load Forecasting Based On Variational Mode Decomposition And Chaotic Grey Wolf Optimization Improved Random Forest Algorithm

Abstract

To enrich short-term load forecasting methods and improve forecasting accuracy, a short-term load forecasting method based on variational mode decomposition and chaotic grey wolf optimization (CGWO) improved random forest (RF) is proposed. Firstly, the traditional GWO is improved by using the improved Logistic chaotic sequence and cooperative attack strategy, and then the CGWO is obtained. Secondly, the CGWO is used to optimize the decision trees and split features in the RF regression model to obtain an improved RF forecasting model. Thirdly, the short-term power load component is obtained by variational mode decomposition (VMD). Finally, the improved RF forecasting model is used for the prediction of short-term power load components, and the prediction results are reconstructed to obtain the final prediction results. The results show that the VMD-CGWO-RF method can effectively predict the short-term power load, the average absolute error is 48.76 megawatt(MW), the root mean square error is 59.53MW, the mean absolute percentage error is 0.66%, while the three indexes of the traditional RF method and CGWO-RF method are larger than VMD-CGWO-RF method, so the proposed method has higher forecasting accuracy.

Keywords

• wolf swarm cooperative attack strategy
• grey wolf optimization
• random forest
• variational mode decomposition
• short-term load forecasting