As cloud service become popular and cost effective throughout the world, Virtual Machine (VM) technology has out staged as the key of many cloud services providers. To maximize data center utilization, cloud data center usually utilizes supervisor to manage virtualized resources. The existing system has issues with higher overhead and computational complexity for load balancing mechanism. Hence, the overall cloud performance is reduced considerably. To overcome the above mentioned issues, in this work, Enhanced Simulated Annealing and Weighted Support Vector Machine algorithm based Cost effective-VM migration (ESA+WSVMCVM) approach is proposed. This research contains main modules are such as system model, virtualization, load balancing and VM migration. System model includes no of VMs, cloud user, CPU, memory usage, no of tasks and no of resources. After construction of system model, virtualization is performed which is used for easy migration of VMs. It provides computing infrastructure resources, such as computing power, data storage, networking, all in the form of web services. Then, load balancing is done by using ESA algorithm which is used to equalize the total workloads over cloud. Load balancing is achieved by transferring tasks from over-loaded nodes to under-loaded nodes. By generating best fitness values of ESA, the balanced loads are provided and it used to optimize the resource use, maximize throughput, minimize processing time. Finally, cost effective VM migration is performed using WSVM algorithm. It is focused to understand the pattern of overload and under load using weight values of SVM and also identifies the VM migration that requires minimal energy expenditure without compromising with quality of services. From the experimental result, it concluded that the proposed ESA+WSVMCVM algorithm provides better cloud performance in terms of higher throughput and lower computational complexity, cost complexity, Mean Square Error (MSE) rate and energy consumption rather than the existing methods