Journal
WIRELESS NETWORKS
Volume 26, Issue 3, Pages 1905-1919Publisher
SPRINGER
DOI: 10.1007/s11276-018-1874-1
Keywords
Cloud computing; Data center; Energy consumption; Host overloaded detection; Service level agreements; and VM selection
Ask authors/readers for more resources
In this paper, we address the problems of massive amount of energy consumption and service level agreements (SLAs) violation in cloud environment. Although most of the existing work proposed solutions regarding energy consumption and SLA violation for cloud data centers (CDCs), while ignoring some important factor: (1) analysing the robustness of upper CPU utilization threshold which maximize utilization of resources; (2) CPU utilization prediction based VM selection from overloaded host which reduce performance degradation time and SLA violation. In this context, we proposed adaptive heuristic algorithms, namely least medial square regression for overloaded host detection and minimum utilization prediction for VM selection from overloaded hosts. These heuristic algorithms reducing CDC energy consumption with minimal SLA. Unlike the existing algorithms, the proposed VM selection algorithm consider the types of application running and it CPU utilization at different time periods over the VMs. The proposed approaches are validated using the CloudSim simulator and through simulations for different days of a real workload trace of PlanetLab.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available