An Optimal Task Scheduling Towards Minimized Cost and Response Time in Fog Computing Infrastructure

Abstract

Due to the transformation and expansion of Internet of Things(IoT), a large number of services are deployed on the edge of the network to provide the services to the end users rather than from the cloud data center since processing the data at the edge can reduce the response time and bandwidth cost while fulfilling the Quality of services(QoS). The fog-cloud computing environment offers promising solution to provision the available resources for IoT based application. Undoubtely Fog computing compliment of cloud computing helps to provide efficient solution to deal with diverse IoT application. However to provide efficient solution in such environment is challenge in different IoT based application such as health care applications, intelligent transportation system and smart cities. Task scheduling and Resource allocation are the NP-hard issues in distributed computing. Each Application consists of several modules that requires resources to execute. However, providing an optimal task scheduling policy in such a heterogeneous system is a NP class problem and has been proposed by different methods like Greedy, meta-heuristic and all nature inspired algorithm for solving an NP-complete problem. The task scheduling problem is a key challenge in the distributed computing system. In this paper, we are trying to map the independent task into the fog layer and our algorithm gives good result if we place the services in fog layer rather than cloud data center. The system resources available may be CPU, RAM, etc by assigning some priority to the task based on its deadline. Also, we have assumed that once a task assigned to a particular node will not leave that until its execution complete. In this paper, we also proposed a three-layer architecture for efficient task scheduling for application such as health care in smart homes