When traffic flow prediction and wireless big data analytics meet

Yuanfang Chen (1) , Mohsen Guizani (2) , Yan Zhang (3) , Lei Wang (4) , Noel Crespi (5, 6, 7, 8) , Gyu Myoung Lee (6, 7, 8) , Ting Wu (1)

1 HDU - Hangzhou Dianzi University
2 University of Idaho [Moscow, USA]
3 UiO - University of Oslo
4 Dalian University of Technology
5 R3S-SAMOVAR - Réseaux, Systèmes, Services, Sécurité
6 TSP - RS2M - Département Réseaux et Services Multimédia Mobiles
7 SAMOVAR - Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux
8 CNRS - Centre National de la Recherche Scientifique

In this article, we verify whether or not prediction performance can be improved by fitting the actual data to optimize the parameter values of a prediction model. Traffic flow prediction is an important research issue for solving the traffic congestion problem in an ITS. Traffic congestion is one of the most serious problems in a city, which can be predicted in advance by analyzing traffic flow patterns. Such prediction is possible by analyzing the real-time transportation data from correlative roads and vehicles. The verification in this article is conducted by comparing the optimized and the normal time series prediction models. With the verification, we can learn that the era of big data is here and will become an important aspect for the study of traffic flow prediction to solve the congestion problem. Experimental results of a case study are provided to verify the existence of the performance improvement in the prediction, while the research challenges of this data-analytics-based prediction are presented and discussed

Mots clés: Time series analysis; Predictive models; Roads; Trajectory

Domaines: Réseaux et télécommunications [cs.NI]

Yuanfang Chen, Mohsen Guizani, Yan Zhang, Lei Wang, Noel Crespi, et al.. When traffic flow prediction and wireless big data analytics meet. IEEE Network, 2019, 33 (3), pp.161 - 167. ⟨10.1109/MNET.2018.1800134⟩. ⟨hal-01998637⟩