Multi-objective dynamic virtual machine consolidation algorithm for cloud data centers with highly energy proportional servers and heterogeneous workload
- Authors: Khan, Md Anit , Paplinski, Andrew , Khan, Abdul , Murshed, Manzur , Buyya, Rajkumar
- Date: 2022
- Type: Text , Book chapter
- Relation: New Frontiers in Cloud Computing and Internet of Things Chapter 3 p. 69-106
- Full Text: false
- Reviewed:
- Description: Present Dynamic VM Consolidation (DVMC) algorithms assume that optimal energy efficiency can be achieved via maximum load on Physical Machines (PMs). Such assumption has become invalid with the advent of the highly energy proportional PMs. Additionally, these algorithms consider only varying resource demand, ignoring dissimilarity of workload finishing time, aka the VM Release Time (VMRT), whereas both aspects are strongly associated with energy consumption. Consequently, traditional algorithms fail to proffer optimal performance under real Cloud scenarios. Although minimization of VM migration brings massive benefit for Cloud Data Center (CDC), it is complete opposite of what is needed to minimize energy consumption through DVMC. As such, our proposed multi-objective Stochastic Release Time aware DVMC (SRTDVMC) algorithm is unique in addressing concomitant minimization of energy consumption and VM migration in the presence of state-of-the-art PMs and heterogeneous workloads. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Exploiting user provided information in dynamic consolidation of virtual machines to minimize energy consumption of cloud data centers
- Authors: Khan, Anit , Paplinski, Andrew , Khan, Abdul , Murshed, Manzur , Buyya, Rajkumar
- Date: 2018
- Type: Text , Conference proceedings , Conference paper
- Relation: 3rd International Conference on Fog and Mobile Edge Computing, FMEC 2018; Barcelona, Spain; 23rd-26th April 2018; p. 105-114
- Full Text:
- Reviewed:
- Description: Dynamic consolidation of Virtual Machines (VMs) can effectively enhance the resource utilization and energy-efficiency of the Cloud Data Centers (CDC). Existing research on Cloud resource reservation and scheduling signify that Cloud Service Users (CSUs) can play a crucial role in improving the resource utilization by providing valuable information to Cloud service providers. However, utilization of CSUs' provided information in minimization of energy consumption of CDC is a novel research direction. The challenges herein are twofold. First, finding the right benign information to be received from a CSU which can complement the energy-efficiency of CDC. Second, smart application of such information to significantly reduce the energy consumption of CDC. To address those research challenges, we have proposed a novel heuristic Dynamic VM Consolidation algorithm, RTDVMC, which minimizes the energy consumption of CDC through exploiting CSU provided information. Our research exemplifies the fact that if VMs are dynamically consolidated based on the time when a VM can be removed from CDC-a useful information to be received from respective CSU, then more physical machines can be turned into sleep state, yielding lower energy consumption. We have simulated the performance of RTDVMC with real Cloud workload traces originated from more than 800 PlanetLab VMs. The empirical figures affirm the superiority of RTDVMC over existing prominent Static and Adaptive Threshold based DVMC algorithms.
Dynamic virtual machine consolidation algorithms for energy-efficient cloud resource management : A review
- Authors: Khan, Md Anit , Paplinski, Andrew , Khan, Abdul , Murshed, Manzur , Buyya, Rajkumar
- Date: 2017
- Type: Text , Book chapter
- Relation: Sustainable Cloud and Energy Services : Principles and Practice Chapter 6 p. 135-165
- Full Text: false
- Reviewed:
- Description: As envisioned by Leonard Kleinrock [1], Cloud computing has transformed the dream of “computing as a utility” into reality, so much so it has turned out as the latest computing paradigm [2]. Cloud computing is called as Service-on-demand, as Cloud Service Providers (CSPs) assure users about potentially unlimited amount of resources that can be chartered on demand. It is also known as elastic computing, since Cloud Service Users (CSUs) can dynamically scale, expand, or shrink their rented resources anytime and expect to pay for the exact tenure of resource usage under Service Level Agreements (SLA). Through such flexibilities and financial benefits, CSPs have been attracting millions of clients who are simultaneously sharing the underlying computing and storage resources that are collectively known as Cloud data centers.