Fully utilizing green energy can remarkably decrease the operational cost of cloudlet providers in provisioning green cloudlet networks (GCNs), which are powered by both green and brown energy. Owing to the spatial and temporal dynamics of energy demands and green energy generation, migrating Avatars (i.e., virtual machines) from green energy deprived cloudlets into green energy over-provisioned cloudlets can reduce the total on-grid energy consumption of GCN. However, Avatar migration itself consumes non-negligible energy consumption. In this letter, we propose the Energy driven AvataR migration (EARN) scheme to reduce the total on-grid energy consumption of GCN by considering the energy consumption of Avatar migrations. The performance of EARN is demonstrated by extensive simulations.
All Science Journal Classification (ASJC) codes
- Modeling and Simulation
- Computer Science Applications
- Electrical and Electronic Engineering
- edge computing
- green energy
- virtual machine migration