To predict air traffic flow reasonably， research is conducted in conjunction with complex network link prediction. First， the time series is converted into a visual graph to obtain the topological feature quantity， and then combined with the algorithms based on local information， path， and random walk， the prediction accuracy in different sectors of Sanya is compared. It is found that the RWR0.85 algorithm has the highest prediction accuracy. Due to the fact that link prediction can only predict possible edges and cannot predict nodes， the D-S evidence theory is introduced to predict traffic values， with a maximum prediction accuracy of 99.85%. The results indicate that the combination of complex network link prediction and D-S evidence theory for predicting air traffic flow is feasible and effective， laying a foundation for further in-depth research.