Optimization of Data and Energy Migrations in Mini Data Centers for Carbon-Neutral Computing

Due to large-scale applications and services, cloud computing infrastructures are experiencing an ever-increasing demand for resources. At the same time, overall power consumption of data centers has been rising beyond 1% worldwide electricity consumption. The usage renewable energy in contributes decreasing their carbon footprint costs. Several green-energy-aware resource allocation approaches have studied recently. None them takes advantage joint migration jobs xmlns:xlink="http://www.w3.org/1999/xlink">energy green increase efficiency. This paper presents optimization approach energy-efficient mini centers. observed momentum around edge makes design geographically distributed highly desirable. Our solution exploits both virtual machines (VMs) migrations between compute nodes These harvesting, storage, transport capabilities. They enable VMs across different nodes. Compared VM alone, joint-optimization reduces utility by up 22%. reduction can reach 28.5% system when integrating less servers. gains demonstrated using simulation a Mixed Integer Linear Programming formulation problem. Furthermore, we show how our sustaining old-generation efficient servers