The IoV sensors generate huge data that are processed by cloud servers, but this leads to high latency and bandwidth occupies. This was the main motivation behind fog computing. Software Defined Network (SDN) was developed to simplify the traditional networks architecture. Sometimes, when a fog server fails to execute some tasks, it sends them to cloud servers while other fog servers are idle. This leads to inefficient utilization of fog computing resources. This paper aims to optimize the resource utilization of fog computing with meeting the deadlines of tasks via assigning them to an optimal fog server using SDN. Moreover, local and global load balance techniques are proposed. The simulation results revealed that our proposed system decreases the transference of tasks to the cloud and as a result decreases the latency and bandwidth consumption.

Keywords