An Improved Min-Min Task Scheduling Algorithm for Load Balancing in Cloud Computing

Abstract

Cloud computing is a model that uses computing resources (CPU, memory, processor etc.) which are delivered as a service over a network internet. It is a new field for large scale distributed computing. In cloud computing, one of the major task is to execute large number of tasks with given available resources to achieve high performance, minimal total time for completion, Minimum response time, effective utilization of resources etc. Keeping all these perspective, we need to design, develop and propose a scheduling algorithm to develop an allocation map to represent the set of tasks on appropriate resources. Though traditional Min-Min algorithm is a simple, yet efficient algorithm that provides a better scheduling to minimize the total time for completion of tasks compared to the other algorithms. However the drawback of this algorithm is the load imbalanced, which is one of the major issue for cloud provider. In this paper, we introduce an improved load balancing algorithm keeping Min-Min algorithm as base in order to reduce the makespan and increase the resource utilization (ILBMM). The proposed method has two different phases, in the first phase traditional min-min algorithm is executed and in second phase it selects the task with maximum completion time and assigns it to appropriate resource to produce better makespan and utilize resource effectively