Dynamic Load Balancing Strategy based on Resource Classification Technique in IaaS Cloud

Abstract

Cloud computing is a utility-based model in the distributed environment which consists of various numbers of resources with heterogeneous servers. The diversity and increasing demands of the user applications lead to increasing resource demands, which makes the whole cloud data center as load imbalanced. The existing algorithms deal with the load distribution in a static and dynamic environment without dealing with a current load of the servers which may balance the load of the servers at certain time interval but not in the long run. So one of the biggest challenges in a cloud environment is to maximize the resource utilization of the servers and balance the load of the whole cloud data center for the long-term process. In order to meet the above-mentioned challenge, in this paper, we have devised a dynamic load balancing strategy based on a baseline neural network technique which will dynamically classify the servers based on the remaining load capacity of the server and deploy the task to the best-fit virtual machine instances on the optimal loaded server. This may minimize the total execution time of the tasks and maximize the resource utilization of the servers while balancing the load of the cloud data center for the long-term process. Finally, we compare the proposed approach over the existing strategies using various performance metrics.