Scalable Processing of Massive Traffic Datasets

The availability of new massive datasets about traffic, coming from Smart Sensor Networks composed of Vehicles, Mobile Phones and other GPS-equipped devices, is enabling the development of novel Intelligent Applications for Mobility. Among these, a hot and recent research topic is to discover vehicular traffic patterns from these datasets, to provide better mobility predictions. Nevertheless, from a practical stance, there are many technological challenges limiting the applicability of these solutions on the market. Especially the scalability and performance of such systems raise major concerns, given the massive amount of spatio-temporal data to be processed. The current industrial solution is to impose constraints and/or simplifications on both the spatial component of the data and on the employed learning algorithms. This has the drawback that not all the potential information is exploited. To overcome this problem, in this chapter we present a scalable architecture aimed at exploit the computational and storage capabilities of the Cloud. Special emphasis is posed on the analysis of the underlying data models we defined to handle massive dataset for providing vehicular traffic predictions. This solution is actually being evaluated in an industrial context.