A novel load balancing strategy of software-defined cloud/fog networking in the Internet of Vehicles

Abstract

The Internet of Vehicles (IoV) has been widely researched in recent years, and cloud computing has been one of the key technologies in the IoV. Although cloud computing provides high performance compute, storage and networking services, the IoV still suffers with high processing latency, less mobility support and location awareness. In this paper, we integrate fog computing and software defined networking (SDN) to address those problems. Fog computing extends computing and storing to the edge of the network, which could decrease latency remarkably in addition to enable mobility support and location awareness. Meanwhile, SDN provides flexible centralized control and global knowledge to the network. In order to apply the software defined cloud/ fog networking (SDCFN) architecture in the IoV effectively, we propose a novel SDN-based modified constrained optimization particle swarm optimization (MPSO-CO) algorithm which uses the reverse of the flight of mutation particles and linear decrease inertia weight to enhance the performance of constrained optimization particle swarm optimization (PSO-CO). The simulation results indicate that the SDN-based MPSO-CO algorithm could effectively decrease the latency and improve the quality of service (QoS) in the SDCFN architecture.