Energy Efficient Virtual Machine Services Placement in Cloud-Fog Architecture

The proliferation in data volume and processing requests calls for a new breed of on-demand computing. Fog computing is proposed to address the limitations of cloud computing by extending processing and storage resources to the edge of the network. Cloud and fog computing employ virtual machines (VMs) for efficient resource utilization. In order to optimize the virtual environment, VMs can be migrated or replicated over geo-distributed physical machines for load balancing and energy efficiency. In this work, we investigate the offloading of VM services from the cloud to the fog considering the British Telecom (BT) network topology. The analysis addresses the impact of different factors including the VM workload and the proximity of fog nodes to users considering the data rate of state-of-the-art applications. The results show that the optimum placement of VMs significantly decreases the total power consumption by up to 75% compared to a single cloud placement.