Makespan and energy based virtual machine scheduling in cloud systems, Bulut sistemlerinde toplam tamamlanma ve enerji tabanli sanal makine çizelgelemesi

Abstract

Cloud computing is one of the newest computing paradigms that emerged after worldwide development of Internet infrastructure. It is a technology that saves both large companies and small and medium scale companies as well as independent developers from the cost of keeping infrastructure hardware up to date and operational while also providing flexibility on resource use as well providing additional opportunity to minimize data losses. While in the future it is evident that demand for cloud computing will be on the rise. These kinds of datacenters due to their nature consume large amounts of energy and even the savings on smallest scales will enable these gigantic centers to save a significant amount of energy in total. If we have a look at the literature we can see green computing is gaining immense popularity over the years. The Cloud Scheduling problem is a proven problem to be NP-Hard aiming to find the best solution for a limited number of cloud resources which could theoretically be serving an unlimited number of user demands. In this study firstly an experimental workload / power consumption model is proposed for a server computer and then two genetic algorithms optimizing makespan and energy consumption are compared on these metrics at different server loads. As a result it has been seen that these two criteria are closely related to each other and it has been determined that optimizing the energy criterion has a more positive effect between 10% and 13% compared to the time criterion optimization at full or near full server loads. In this way it has been shown that significant energy savings can be achieved by using energy optimization as an objective function at high server loads. © 2024 Elsevier B.V. All rights reserved.