Prediction Of Jiangsu's Energy Demand Based On Improved GM(1,N) Model

Prediction is based on the past and present development laws of objective things,with the help of scientific methods to describe and analyze their future development trends and conditions,and to form scientific assumptions and judgments.Grey system theory has been established for more than 30 years,and has formed a relatively perfect theoretical system.As one of the important research directions of grey theory,grey prediction has been widely used in various fields.Grey forecasting model is a method of establishing mathematical model and making forecasting according to specific conditions through incomplete and less systematic information.In our daily life,when we need to formulate development policies and specific policies,or analyze and make decisions on some important issues,we need to use scientific methods to predict.After a long period of development,the scientific and accuracy of grey forecasting methods have been tested,and have been constantly improved by scholars.GM(1,N),as a widely used model in grey prediction,has been applied to various practical scenarios.However,the classical GM(1,N)model has some shortcomings.For example,the prediction accuracy is not very stable,and sometimes there may even be deviations.For this reason,scholars have made some improvements from different perspectives,but most of these optimization methods are aimed at one aspect of the improvement,so they have one-sided shortcomings.In view of the above problems,this paper proposes a combinatorial optimization method,which considers the interaction between the relevant factors and the influence of dummy variables on the feature sequence,optimizes the background value of the model,and discusses the parameter solving method and application of the new model.Based on the energy demand data of Jiangsu Province,the classical model,the model with only interaction effect,the model with only virtual variable control and the improved GM(1,N)model are used to calculate and compare the errors.The results show that the improved model is superior to other models in accuracy,and the future energy demand of Jiangsu Province is forecasted by the improved model.