A PSO Based VM Resource Scheduling Model for Cloud Computing

Cloud computing, a new paradigm for utility computing, has brought a revolutionary change in the IT industry by enabling the elastic on demand resource provisioning of computing resources. As cloud infrastructure heavily relies on virtualization technology, there is a need for an efficient and effective virtual machine scheduling strategy. Virtual machine scheduling problem can be defined as an allocation of a set of virtual machines (VMs) to a set of physical machines (PMs). The proposed work focuses on PSO based VM scheduling strategy for VM placement in cloud infrastructure. The strategy focuses on efficient VM allocation to physical servers in order to minimize the total resource wastage and the number of servers used. Simulation experiments were conducted to observe the allocation of VMs to the servers and to evaluate the proposed algorithm with respect to performance and scalability. The results are compared with Best-Fit, First-Fit and Worst-Fit placement strategies. Simulation study conducted to evaluate the performance reveals the effectiveness of the model.