Abstract: A new grey power model is proposed for modeling periodic small sample systems. In the modeling process, a trigonometric function is introduced to identify the periodicity characteristics of the data, and the specific time response formula and modeling steps are given. At the same time, in order to minimize the average relative error, the least square method and genetic algorithm are used to optimize and solve each parameter. Finally, the model is applied to forecast the traffic flow of the Hengda Expressway in Hebei Province and the PM2.5 content of air pollutants in Tianjin. The results are compared with those of other models. The results show that the proposed model has higher prediction accuracy, which further verifies the validity of the model. 

Key words: Grey Prediction, Periodic, Power Model, Genetic Algorithm