Branch Mathematics and Statistics Faculty and Staff Publications
Document Type
Article
Publication Date
2024
Abstract
The dynamic landscape of cloud computing design presents significant challenges regarding power consumption and quality of service (QoS). Virtual machine (VM) consolidation is essential for reducing power usage and enhancing QoS by relocating VMs between hosts. OpenStack Neat, a leading framework for VM consolidation, employs the Modified Best-Fit Decreasing (MBFD) VM placement technique, which faces issues related to energy consumption and QoS. To address these issues, we propose an Energy Efficient VM Consolidation (EEVMC) approach. Our method introduces a novel host selection criterion based on the incurred loss during VM placement to identify the most efficient host. For validation, we conducted simulations using real-time workload traces from Planet-Lab and Materna over ten days, leveraging the latest CloudSim toolkit to compare our approach with state-of-the-art techniques. For Planet-Lab’s workload, our EEVMC approach shows a reduction in energy consumption by 80.35%, 59.76%, 21.59%, and 7.40%, and fewer system-level agreement (SLA) violations by 94.51%, 94.85%, 47.17%, and 17.78% when compared to Modified Best-Fit Decreasing (MBFD), Power-Aware Best Fit Decreasing (PABFD), Medium Fit Power Efficient Decreasing (MFPED), and Power-Efficient Best-Fit Decreasing (PEBFD), respectively. Similarly, for Materna,EEVMCachieves a reduction in energy consumption by 16.10%, 61.0%, 4.94%, and 4.82%, and fewer SLA violations by 76.99%, 88.88%, 12.50%, and 48.65% against the same benchmarks. Additionally, Loss-Aware Performance Efficient Decreasing (LAPED) significantly reduces the total number of VM migrations and SLA time per active host, indicating a substantial improvement in cloud computing efficiency.
Publication Title
IEEE Access
Volume
12
First Page
105234
Last Page
105245
Language (ISO)
English
Keywords
Virtual machine consolidation, quality of service, energy efficient, VM migration, placement algorithm, OpenStack cloud
Recommended Citation
Rehman, Attique Ur; Songfeng Lu; Mubashir Ali; Florentin Smarandache; Sultan S. Alshamrani; Abdullah Alshehri; and Farrukh Arslan.
"EEVMC: An Energy Efficient Virtual Machine Consolidation Approach for Cloud Data Centers."
IEEE Access
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
