An Improved Job Scheduling in Cloud Environment using Auto-Associative-Memory Network

Abstract

Cloud computing plays a vital role in the field of information sharing through the internet. In this current scenario, some of the major problems in cloud computing are job scheduling, resource clustering, storage allocation, VM migration etc. In this paper, problems such as job scheduling and resource clustering are concentrated. Arrival time, waiting time, response time, makespan time, communication time, utilization time, throughput time of a job are considered while scheduling the jobs in a cloud environment. A good scheduling policy should achieve minimum makespan time. Efficiency of the storage and computation nodes is considered during the process of resource clustering. In this regard, a near optimal approach is proposed to perform job scheduling and resource clustering. Hopfield neural network (Auto-Associative-Memory network) is used along with equivalence partitioning recurrent node weight (EPRNW) algorithm to schedule the jobs in an excellent manner. The comparative study and performance evaluation is done between the existing approaches and proposed approach. The proposed approach minimizes the makespan time by using continuous Hopfield neural network to achieve the near optimal scheduling and equivalence partitioning recurrent node weight algorithm is used to identify the corresponding computation nodes instead of random selection of computation nodes for resource clustering. Efficiency of scheduling process is maximized and resource clustering is performed rapidly by using the proposed algorithm.