In modern researchers, cloud parallel data processing has emerging resource that to be one of the problematic application for Infrastructure-as-a-Service (IaaS) clouds. Major Cloud processing companies include starting incorporate frameworks using VM models for parallel data processing in their resource portfolio creation to easy for a client to access these services and to set out their programs. The growing computing requires from multiple requests on the main server has lead to excessive power utilization. The waiting resource in the long-term sustainability of Cloud like infrastructures in provisions of energy cost but also from cloud environmental perspective. The trouble can be addressed to require with high energy consumption resource sharing infrastructures, but in the process of resources are dynamically switch to new infrastructure. Switching is not enough to cost efficient and also need time sharing green consuming. Cloud being consists of several virtual centers like VMs under the different administrative domain, make a problem more difficult. Thus, for the reduction in energy consumption, this propose address the challenge by effectively distributing compute-intensive parallel applications on the cloud. To propose a Meta-scheduling algorithm, this exploits the heterogeneous nature of Cloud to achieve the reduction in energy consumption as the green cloud. This intent addresses these challenges by proposing a virtual file system specifically optimized for virtual machine image storage. It is based on a lazy transfer scheme coupled with object versioning that handles snapshot ting transparently in a hypervisor-independent fashion, ensuring high portability for different configurations.