Energy-Efficient Task Scheduling Using Fault Tolerance Technique for IoT Applications in Fog Computing Environment

In the n-tier framework, data generated by the sensors requires immediate execution. The processing elements need powerful resources to entertain incoming requests. Fog computing, unlike cloud computing, provides low latency for real-time applications. However, data generated by the real-time Internet of Things (IoT) devices significantly impacts the fog devices. The data generated must be processed by the fog devices with quick response time, minimum delay, and energy consumption and send it back to the end-users with high reliability and success rate. However, devices fail due to damage or internal state of a fog device which measures incorrectly or causes destruction which badly affects the overall system performance. The end-to-end transmission requests from the IoT devices require immediate response with minimal delay, execution cost, and energy consumption in spite the occurrence of fog devices failure. In this article, we propose a novel energy efficient task scheduling algorithm based on reactive fault tolerance in an n-tier fog computing framework for IoT applications to enhance the overall fog computing performance. In case of fog device failure, the assigned task is rescheduled to other executable fog nodes without further delay. The proposed framework is based on the modified particle swarm optimization and is designed and evaluated in iFogSim. The main objective of the proposed technique is to reduce energy consumption, latency, network bandwidth utilization, and increase system reliability and success rate. Several experiments have been carried out by taking a maximum of ten iterations based on which it is concluded that the proposed technique reduces energy consumption by 3%, latency by 5%, network bandwidth utilization by 3%, and increases the system reliability by 2% and success rate by 8%.