Self-adaptive task distribution for load balancing using HABACO in cloud

In the world full of competition, there is huge amount of processing, storage and memory requirements because of the generation of huge amount of data, which is in the form of structured, semi structures, quasi structured and unstructured from the heterogeneous and dynamic data sources like face book, linked in, twitter, sql server. This was the reason that IT people in large organizations had moved to the cloud to fulfill their requirements for the successful completion of needs of the clients and the modern era. This was made possible by the emergence of a vast ocean of cloud applications and infrastructure environment. As the data sets are growing in millions of terabytes per day and there is huge number of applications run on machines in data centers, so the load on the servers is growing in direct proportion. This is defeating the configuration of servers running in the data centers. To counter this problem, this paper proposes a hybrid optimization algorithm HABACO, which is the combination of modified Ant Colony and Artificial Bee optimization algorithm, does not only automatically balance the load on servers running in data centers rather it will also ensure reduction in the live dynamic migration of Virtual machine and its applications. HABACO combines search optimization from modified ACO and accuracy of AB to drive it to benefit with lower cost (IOPS), reduce response time and performance of servers running inside the data centers located heterogeneous locations across the globe.