PM2.5 Prediction of Innovation Priority Discrete Nonlinear Gray Model Based on Gray Wolf Optimization Algorithm

Abstract

PM2.5 is one of the main factors of air pollution, so the prediction of PM2.5 is of great significance. For this reason, the innovation priority discrete nonlinear gray model based on gray wolf optimization algorithm is established, which is based on the innovation priority principle in the gray system principle. Try to optimize the discrete nonlinear gray model, and use the gray wolf optimization algorithm to solve the innovation priority parameters. First, the basic theory of discrete nonlinear gray model is proposed. On this basis, the innovation priority principle is used to improve the cumulative generation sequence, and the cumulative generation with parameters is defined. Finally, using the minimum error criterion, the gray wolf optimization algorithm is used to solve the parameters. Take the monthly PM2.5 data and daily PM2.5 data of Mianyang City, Chengdu City, Zigong City and Panzhihua in Sichuan Province as examples. Apply the model to perform PM2.5 forecast analysis, and calculate the absolute average percentage between the predicted value and the observed value Error, and compare with the traditional gray model. The analysis shows that the established model has achieved good results, which verifies the practicability and reliability of the proposed model.