Performance Evaluation of Virtual Machines Instantiation in a Private Cloud

Author(s):  
Eliomar Campos ◽  
Rubens Matos ◽  
Paulo Maciel ◽  
Igor Costa ◽  
Francisco Airton Silva ◽  
...  
Author(s):  
Gabriel Tomiatti Andreazi ◽  
Julio Cezar Estrella ◽  
Sarita Mazzini Bruschi ◽  
Antonio Marcos Almeida Ferreira ◽  
Welington da Silva Martins

2017 ◽  
Vol 8 (3) ◽  
pp. 53-73
Author(s):  
Raza Abbas Haidri ◽  
Chittaranjan Padmanabh Katti ◽  
Prem Chandra Saxena

The emerging cloud computing technology is the attention of both commercial and academic spheres. Generally, the cost of the faster resource is more than the slower ones, therefore, there is a trade-off between deadline and cost. In this paper, the authors propose a receiver initiated deadline aware load balancing strategy (RDLBS) which tries to meet the deadline of the requests and optimizes the rate of revenue. RDLBS balances the load among the virtual machines (VMs) by migrating the request from the overloaded VMs to underloaded VMs. Turnaround time is also computed for the performance evaluation. The experiments are conducted by using CloudSim simulator and results are compared with existing state of art algorithms with similar objectives.


Automatika ◽  
2020 ◽  
Vol 61 (3) ◽  
pp. 425-435
Author(s):  
Josip Balen ◽  
Krešimir Vdovjak ◽  
Goran Martinović

Author(s):  
Hidenori Umeno ◽  
Maria C. Parayno ◽  
Koudai Teramoto ◽  
Masato Kawano ◽  
Hiraku Inamasu ◽  
...  

Author(s):  
Adib Habbal ◽  
Siti Aminah Abdullah ◽  
Emmanuel O.C. Mkpojiogu ◽  
Suhaidi Hassan ◽  
Nabil Benamar

Cloud computing has attracted the attention of educational and research institutions as a way to support modern trends in teaching and learning. This article describes the performance assessment of a private cloud within a university environment using the Web of System Performance (WOSP) model. A survey was carried out to measure the respondents' attitude towards the use of private cloud in which students and experts serve as sample. Testing was conducted by designing a virtual lab consisting of a number of virtual machines operated by a selected sample. The results showed that the usage of cloud computing in university has good perceived system performance judging from how it fares in the constituent parts of the WOSP model. Furthermore, the study revealed that usability and flexibility outperformed criterion like security. Moreover, several non-functional criteria outperformed functionality. In short, the knowledge and results presented from assessing a private cloud using WOSP model could be beneficial for users, designers and managers of private clouds especially in universities.


2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Shyamala Loganathan ◽  
Saswati Mukherjee

Cloud computing is an on-demand computing model, which uses virtualization technology to provide cloud resources to users in the form of virtual machines through internet. Being an adaptable technology, cloud computing is an excellent alternative for organizations for forming their own private cloud. Since the resources are limited in these private clouds maximizing the utilization of resources and giving the guaranteed service for the user are the ultimate goal. For that, efficient scheduling is needed. This research reports on an efficient data structure for resource management and resource scheduling technique in a private cloud environment and discusses a cloud model. The proposed scheduling algorithm considers the types of jobs and the resource availability in its scheduling decision. Finally, we conducted simulations using CloudSim and compared our algorithm with other existing methods, like V-MCT and priority scheduling algorithms.


2015 ◽  
Vol 7 (2) ◽  
pp. 117-132
Author(s):  
Stanislaw Lota ◽  
Marcin Markowski

Abstract Virtualization of physical network devices is a relatively new technology, that allows to improve the network organization and gives new possibilities for Software Defined Networking (SDN). Network virtualization is also commonly used for testing and debugging environments, before implementing new designs in production networks. Important aspect of network virtualization is selecting virtual platform and technology, that offer maximal performance with minimal physical resource utilization. This article presents a comparative analysis of performance of the virtual network created by the virtual CSR1000v and virtual machines running Windows 8.1 on two different virtual private cloud platforms: VMware vSphere 5.5 and Microsoft Hyper-V Server 2012 R2. In such prepared testbed we study the response time (delay) and throughput of virtual network devices.


Sign in / Sign up

Export Citation Format

Share Document