Energy Efficient DVFS with VM Migration

Cloud Computing offers efficient computing with Pay-as-you-go models. It is now easy for consumer to start with- out need of initial setup, which saves a lot of infrastructure cost. As consumers are subscribing to the cloud, the load is increasing on the data centers, thus data centers are in need for more resources and more power. And all this process is increasing the carbon footprint and polluting environment. Now the time has come when we require efficiency in term of power. We really need to look for mechanism how the power can me be managed to be more efficient. This paper suggests the Green Architecture Framework and also suggests to use of Dynamic Voltage Frequency Scaling (DVFS) as per the load requirement which results in better energy efficiency

Scheduling of Tasks (CLOUDLETS) in Hetrogeneous Processing Cloud Environment

Scheduling in cloud environment is a big challenge, it has two flavors in cloud environment one to schedule the placement of the virtual machines (VM) and second is the placement of cloudlet or tasks in the right virtual machine for the fast execution. In first type of scheduling to save the energy in the DataCenter it is always a good idea to re-arrange the running VM’s on the underlying physical machines, so the underload physical machine can go to sleep to save energy. So, the assignment of the VM from the underloaded physical machine to other is a challenge. In second the placement of cloudlet to the VM for execution, the decision to VM is crucial. In DataCenter, the underlying environment is heterogeneous, it is a challenge to use all the VM which are now old and new high-end specs VM. So, balancing the tasks assignment is challenging. In the proposed work the placement of the tasks is taken up, the tasks are picked- up for execution on the FCFS basis and our algorithm assigns all the tasks to the VM which is providing the minimum execution time. It calculates the time of execution from all the VM available and calculates the time to finish the previous assigned or under execution tasks to find the minimum execution time. We will see the algorithm working in load scenarios.