Abstract
Over the last few years, we have witnessed an exponential increase in the computing and storage capabilities of smart devices that has led to the popularity of an emerging technology called edge computing. Compared to the traditional cloud-computing- based infrastructure, computing and storage facilities are available near end users in edge computing. Moreover, with the widespread popularity of unmanned aerial vehicles (UAVs), huge amounts of information will be shared between edge devices and UAVs in the coming years. In this scenario, traffic surveillance using UAVs and edge computing devices is expected to become an integral part of the next generation intelligent transportation systems. However, surveillance in ITS requires uninterrupted data sharing, cooperative decision making, and stabilized network formation. Edge computing supports data processing and analysis closer to the deployed machines (i.e., the sources of the data). Instead of simply storing data and missing the opportunity to capitalize on it, edge devices can analyze data to gain insights before acting on them. Transferring data from the vehicle to the edge for real-time analysis can be facilitated by the use of UAVs, which can act as intermediate aerial nodes between the vehicles and edge nodes. However, as the communication between UAVs and edge devices is generally done using an open channel, there is a high risk of information leakage in this environment. Keeping our focus on all these issues, in this article, we propose a data-driven transportation optimization model where cyber-threat detection in smart vehicles is done using a probabilistic data structure (PDS)- based approach. A triple Bloom filter PDS- based scheduling technique for load balancing is initially used to host the real-time data coming from different vehicles, and then to distribute/collect the data to/from edges in a manner that minimizes the computational effort. The results obtained show that the proposed system requires comparatively less computational time and storage for load sharing, authentication, encryption, and decryption of data in the considered edge-computing-based smart transportation framework.