Cloud computing is a service model in internet that provides virtualized resources to its clients. These types of servicing give a lot of benefits to the cloud users where they can pay as per their use. Even though they have benefits, they also face some problems like receiving computing resources, which is guaranteed on time. This time delay may affect the service time and the makespan. Thus, to reduce such problems, it is necessary to schedule the resources and then allocate it to using an optimized hypervisor. Here, the proposed method is used to do the above-mentioned problem. First, the available resources are clustered with respect to their characteristics. Then the resources are scheduled using this method. Finally, with respect to that of the clients request the resources, the resources are allocated. Here, the cost is the fitness of the allocation.
A simple heuristic for load balancing in parallel processing networks with highly variable service time distributions
