Load-aware resource scheduling in fog computing based delay-sensitive IOT networks

Abstract

Internet of Things (IoT), with its capability to connect anything, anywhere, anytime, bringing in revolutionary changes in data collection, processing and utilization. IoT networks generate a huge amount of data, which is difficult to process and store on IoT devices. Cloud computing with its huge availability of resources, can process and store these huge volumes of data. However, owing to the long distance between the cloud and IoT devices, the cloud computing suffers the issues like high latency, network congestion and unreliability. To address these issues, fog computing, which is a decentralized computing paradigm has been proposed as an extension to cloud computing. To utilize the fog resources efficiently and to avoid over-utilization and under-utilization of resources, this paper proposes a resource scheduling algorithm which is capable of balancing the load on fog nodes while satisfying the delay requirements of IoT applications. Extensive simulations are conducted to evaluate the performance of the proposed method. The simulation results establish that the load is almost equally distributed among the fog nodes in the network in most of the traffic arrival scenarios.