A Scalable lnternet-of-Vehicles Service over Joint Clouds

Since the Internet of Vehicles (IoV) technology has recently attracted huge research attention, IoV services that can collect, process data and further provision services are increasingly becoming the mainstream. Considering the process efficiency, geo-distributed data is typically collected and exploited on different Clouds, making it significantly essential for IoV application to be deployed on multiple Clouds whilst system components still function well and jointly work. In this paper, we provide a scalable IoV system deployment in the joint Cloud environment where cloud vendors collaboratively cooperate as an alliance. In particular, system components are independently deployed in accordance with the data placement and resource capacities etc. A multi-replication mechanism is utilized to achieve the cross-cloud parallel processing, thereby effectively handling the scalability issues in the massive-scale vehicle data processing. Furthermore, we adopt the multi-source data fusion to facilitate the accuracy of IoV data analytics. We demonstrate the effectiveness of the proposed approaches through real-world use cases including fleet distribution management and passenger demands prediction.