CLOUD COMPUTING LOAD BALANCING MODEL WITH HETEROGENEOUS PARTITION

Cloud computing is an on demand service in which shared resources, information, software and other devices are provided according to the clients requirement at specific time . In the cloud computing paradigm, the scheduling of computing resources is a diffi cult part of cloud computing field. With increment in number of users and the type of applications on the cloud computing, effective utilization of resources in the system becomes a critical concern. In order to improve the performance of the whole cloud e nvironment, Load Balancing algorithms are needed to distribute the load evenly across all the partition in cloud according to number of nodes . In this system Cloud having numbers of nodes and that is distributed in many partitions according to need. Syste m having clouds each cloud having different capacity. In this system admin can chnage the size of cloud dynamically, it can change the size of any cloud according to need. Admin upload the jobs on to cloud then it redirect the job on different cloud accor ding to load degree calculation cloud status will change from idle to normal and from normal to overloaded if there is no free load available on that cloud. When partition is overloaded at that time load is distr ibuted over the other id l e nodes. As job is redirected towards the cloud, cloud active status will increase. If all partition in the system is overloaded then system gives message maximum connection are crossed. Many algorithms are available for load balancing like Static load balancing and Dynamic load balancing. System used round robin with load degree evaluation algorithm which is dynamic load balancing algorithm. Users not allowed upload the file but he can view the file directly without Login . The load balancing criteria have significant influe nce on the performance, and they can change the behavior of the system . The load balancing model given in this article is aimed at the cloud which has numerous nodes with distributed computing resources in many different geographic locations. Thus, this mo del divides the cloud into several cloud heterogeneous partitions. When the environment is very large and complex, these divisions simplify the load balancing. The cloud has a main controller that chooses the suitable partitions for arriving jobs while the balancer for each cloud partition chooses the best load balancing strategy. The Round Robin algorithm is used here because it is fairly simple