Department of Information Science, College of Life Sciences, Kuwait University, Kuwait
Email: kalimuddin.qureshi@ku.edu.kw (K.Q.); latif00@yahoo.com (A.A.); p.manuel@ku.edu.kw (P.M.)
*Corresponding author
Manuscript received June 30, 2024; revised August 13, 2024; accepted January 8, 2025; published May 8, 2025
Abstract—Cloud computing has become a norm for enterprises due to its significant advantages in infrastructure management, performance, and expenses. Cloud data centers consume significant power and go against the principles of green computing. It requires efficient management to minimize the environmental impact. Thus, green computing has become an interesting field of research in cloud computing. However, green computing is bundled with a performance-energy trade-off: job completion rate versus power consumption rate. This paper precisely focuses on this topic. A graphical user interface that utilizes the CloudSim simulator to evaluate the performance of various Virtual Machine (VM) power management policies in data centres has been developed. In our study, we test seven VM allocation policies: Dynamic Voltage and Frequency Scaling (DVFS), Interquartile Range (IQR), Local Regression (LR), Local Regression Robust (LRR), Median Absolute Deviation (MAD), Static Threshold (THR), and Single Threshold (STR). We also evaluate the performance of five VM selection policies: None, Maximum Correlation (MC), Minimum Migration Time (MMT), Maximum Utilization (MU), and Random Selection (RS). Utilizing CloudSim’s thirty-six different power management mechanisms across seven designed scenarios, we measure each policy’s power consumption and job completion rates for the analysis. The DVFS mechanism has proven to be the most effective method for conserving power. While preserving the power, its job completion rate is significantly compromised. Our proposed model measures the excessive power consumed by a power management mechanism residing in the system and concludes that there is no clear leader based on the performance-energy trade off.
Keywords—green computing, data center, cloud computing, Virtual Machine (VM) migration, green computing trade-off
[PDF]
Cite: Kalim Qureshi, Abdulatif Albusairi, and Paul Manuel, "Empirical Evaluation of Virtual Machine Migration Policies on Power- and Time-Management in Cloud Computing," International Journal of Computer Theory and Engineering, vol. 17, no. 2, pp. 83-90, 2025.
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
