Statistical approach toward achieving green cloud computing: Virtualization in single server environment

The rapid growth of trending technologies, such as information technology (IT) and digital electronics, creates a massive demand for cloud computing. This results in the tremendous growth in new data centers, which consequently causes a significant increase in power consumption due to the continuous operation of such centers. When power consumption spikes up constantly, it will affect the environment. This paper aims to create multiple algorithms which run on a single server with low power consumption and a stable process. The method applied in this paper was virtualization with a statistical approach. Four main hypotheses were created to achieve the research objectives relating to the main properties of control limit, load balancing, process setting, and process capability. Furthermore, the paper came up with several novel approaches to dynamic threshold setting, the best matching of load balancing between VM Selection and VM Placement, and a special step to optimi ze the process setting via the pre-control method. The paper aims to create an algorithm that can cater to any incoming workload to the server for the entire year without impacting the power consumed by the single server. Besides focusing on power consumption produced by the single server, the performance stability of the server was also taken into consideration. The process capability theory a nd pre-control method were applied to monitor and optimize the overall power consumption and stable performance. This research shows that the novel approach of dynamic threshold setting was able to produce a significant reduction in power consumption by the single server. It seemed that the novel dynamics threshold setting is 87.5% better than the static threshold setting. In addition to that, load balancing optimization was proven to achieve green cloud computing with low power consumption, where the best load balancing is MU/LRR. This paper also discovered that as the range of yellow and green regions at the pre-control setting increased, the desired system became more stable. Lastly, the concept of process capability failed to optimize the stability of the system.