Edge Computing-Enabled Resource Provisioning for Video Surveillance in Internet of Vehicles

Abstract

As a novel technology, Internet of Vehicles (IoV) is employed to gather real-time traffic information for drivers from sensors and video surveillance devices with image processing, circumstances analysis and events recognition. In spite of multiple advantages of IoV, preprocessing the huge data may demand abundant computation resources for video surveillance devices. Migrating tasks to remote servers for performing is efficient to solve this problem, but it needs high network bandwidth, which causes traffic congestion and delay. Edge computing has capability to enhance processing performance, which complements video surveillance device and addresses numerous shortcomings. Nevertheless, edge computing for video surveillance remains a challenge to achieve lowlatency and load balance through limited amount of edge servers. To handle this challenge, an Edge computing-enabled Resource Provisioning Method (ERPM) for Video Surveillance in IoV is proposed in this paper. Technically, SPEA2 (improving the Strength Pare to Evolutionary Algorithm) is picked to solve the multi-objective optimization problem aiming at minimizing the time consumption and optimizing load balance. Finally, experimental simulation for Evolution algorithm demonstrate the appropriation and efficiency of ERPM.

Task Migration Based on Reinforcement Learning in Vehicular Edge Computing

“…To determine whether the computing load is distributed fairly among the VECSs in the system, load balance is measured by the deviation of the computing load at each VECS [15]. In this study, we define the load-balancing factor LB as follows:…”