Efficiently Synchronizing Virtual Machines in Cloud Computing Environments

Author(s):  
Shuntaro Tonosaki ◽  
Hiroshi Yamada ◽  
Kenji Kono
Author(s):  
I. P. Oladoja ◽  
O. S. Adewale ◽  
S. A. Oluwadare ◽  
E. O. Oyekanmi

Cloud computing environments provide an apparition of infinite computing resources to cloud users so that they can increase or decrease resource consumption rate according to their demands. In the Cloud, computing resources need to be allocated and scheduled in a way that providers can achieve high resource utilization and users can meet their applications’ performance requirements with minimum expenditure. Due to these different intentions, there is the need to develop a scheduling algorithm to outperform appropriate allocation of tasks on resources. The paper focuses on the resource optimization using a threshold-based tournament selection probability for virtual machines used in the execution of tasks. The proposed approach was designed to create metatask and the proposed algorithm used was Median-Based improved Max-Min algorithm. The experimental results showed that the algorithm had better performance in terms of makespan, utilization of resources and throughput. The load balance of tasks was also fairly distributed on the two datacenters.


2019 ◽  
Vol 93 ◽  
pp. 442-459 ◽  
Author(s):  
Mohammad Aldossary ◽  
Karim Djemame ◽  
Ibrahim Alzamil ◽  
Alexandros Kostopoulos ◽  
Antonis Dimakis ◽  
...  

The cloud computing paradigm has settled to a stable stage. Due to its enormous advantages, services based on cloud computing are getting more and more attraction and adoption by diversified sectors of society. Because of its pay per use model, people prefer to execute various data crunching operations on high end virtual machines. Optimized resource management however becomes critical in such scenarios. Poor management of cloud resources may affect not only customer satisfaction but also wastage of available cloud infrastructure. An optimized resource sharing mechanism for collaborated cloud computing environments is suggested here. The suggested resource sharing technique solves starvation issue in inter cloud load balancing context. In case of occurrence of starvation problem, the suggested technique resolves the issue by switching under loaded and overloaded virtual machines between intra cloud and inter cloud computing environment.


Author(s):  
Kranthi Kumar. K ◽  
R. Rindha Reddy ◽  
Kurumaddali Sushmitha

Cloud Computing (CC) is the advancement of the Grid Computing (GC) worldview in the direction of administration arranged structures. The phrasing connected to this sort of handling, while portraying shared resources, alludes to the idea of Service of X. Such assets are accessible on interest and at an altogether low cost contrasted with self-conveyance of individual segments. CC is found everywhere in current situations, from vast scale associations to a just little scale business, everybody is equipping themselves cloud. Due to its effortlessness, observing and support over remote association, expansive territory inclusion. Cloud can be any sort Software as an administration, stage as an administration, foundation as an administration dependent on its use. High Performance Computing (HIPECO) implies the accumulation of computational capacity to build the capacity of handling substantial issues in science, designing, and business. HIPECO on the cloud permits performing on interest HIPECO errands by superior clusters in a cloud atmosphere. Currently, CC arrangements (e.g., Microsoft Azure, Amazon EC2) enable the users to make use of only the fundamental storage and computational utilities. They prevent the allowance of custom adjustments of the topology designs or parameters of the system. The associations structures of the nodes in HIPECO clusters ought to give a quick bury node correspondence. It is vital that adaptability is safeguarded also. In a foundation, as an administration, virtualization viably maps virtual machines to the physical machines. In spite of the fact that it is difficult, undertaking for hypervisor to choose fitting host to serve up and coming virtual machine is a must requirement. In this paper, our main aim is to examine different techniques/types of cluster topology mapping and their necessities in numerous Cloud situations to accomplish higher dependability along with adaptability of utilization which is executed inside Cloud resources (CR), HIPECO resource allocation (RA) on the cloud clusters and Cluster based designation procedure.


Electronics ◽  
2020 ◽  
Vol 9 (4) ◽  
pp. 686
Author(s):  
JongBeom Lim ◽  
DaeWon Lee

As current data centers and servers are growing in size by orders of magnitude when needed, load balancing is a great concern in scalable computing systems, including mobile edge cloud computing environments. In mobile edge cloud computing systems, a mobile user can offload its tasks to nearby edge servers to support real-time applications. However, when users are located in a hot spot, several edge servers can be overloaded due to suddenly offloaded tasks from mobile users. In this paper, we present a load balancing algorithm for mobile devices in edge cloud computing environments. The proposed load balancing technique features an efficient complexity by a graph coloring-based implementation based on a genetic algorithm. The aim of the proposed load balancing algorithm is to distribute offloaded tasks to nearby edge servers in an efficient way. Performance results show that the proposed load balancing algorithm outperforms previous techniques and increases the average CPU usage of virtual machines, which indicates a high utilization of edge servers.


Sign in / Sign up

Export Citation Format

Share Document