Traffic flow prediction has been applied into many wireless communication ap-plications (e.g.,smart city, Intet of Things). With the development of wireless communi-cation technologies and artificial intelligence, how to design a system for real-time traffic flow prediction and receive high accuracy of prediction are urgent problems for both re-searchers and equipment suppliers. This paper presents a novel real-time system for traffic flow prediction. Different from the single algorithm for traffic flow prediction, our novel sys-tem firstly utilizes dynamic time wrapping to judge whether traffic flow data has regularity, realizing traffic flow data classification. After traffic flow data classification, we respective-ly make use of XGBoost and wavelet transform-echo state network to predict traffic flow da-ta according to their regularity. Moreover, in order to realize real-time classification and prediction, we apply Spark/Hadoop computing platform to process large amounts of traffic data. Numerical results show that the proposed novel system has better performance and higher accuracy than other schemes.