Conference PaperPDF Available

Improving Cloud Computing Virtual Machines Balancing through Hosts and Virtual Machines Similarities

Authors:

Abstract

Quality of service is one of the major concerns in cloud computing. Virtual machines (VMs) balancing techniques can help reduce service degradation in cloud computing environments. Several works have presented cloud computing balance techniques; however, only a few used the similarity between VMs and physical hosts to map VMs migrations. In addition, most proposals do not consider the size, dynamism, and heterogeneity of the cloud when developing a management technique. We present a cloud computing VMs balancing algorithm that uses the similarity between VMs and physical hosts to create the map of migrations. Furthermore, the proposal takes into account the size, dynamism, and heterogeneity of the cloud when mapping VMs migrations; thus the proposal is developed in a distributed fashion, enabling the processing of each cluster at a time. To evaluate the proposal, we used the Google cluster data set. Experiments demonstrate that the proposed technique can improve the balance of allocated resources; thus helping reduce service degradation. Moreover, the runtime of the algorithm indicates that it is feasible to be used in a real cloud computing environment with hundreds of physical servers and virtual machines.
11/19/17, 7'56 PMImproving Cloud Computing Virtual Machines Balancing through Hosts and Virtual Machines Similarities - IEEE Conference Publication
Page 1 of 3http://ieeexplore.ieee.org/document/8036725/?reload=true
Institutional Sign In
IEEE.org IEEE Xplore Digital Library
|IEEE-SA
|IEEE Spectrum
|More Sites
| Cart (0) Create Account
| Personal Sign In
|
Browse Conferences > Services (SERVICES), 2017 IEE...
Improving Cloud Computing Virtual Machines Balancing
through Hosts and Virtual Machines Similarities
Sign In or Purchase
to View Full Text
54
Full
Text Views
Related Articles
On aspect-orientation in distributed real-time
dependable systems
Reconfiguration of resources in middleware
View All
3
Author(s)
Gabriel Beims Bräscher ; Rafael Weingärtner ; Carlos Becker Westphall
View All Authors
Abstract:
Quality of service is one of the major concerns in cloud computing. Virtual machines (VMs) balancing techniques can help reduce service
degradation in cloud computing environments. Several works have presented cloud computing balance techniques, however, only a few used the
similarity between VMs and physical hosts to map VMs migrations. In addition, most proposals do not consider the size, dynamism, and
heterogeneity of the cloud when developing a management technique. We present a cloud computing VMs balancing algorithm that uses the
similarity between VMs and physical hosts to create the map of migrations. Furthermore, the proposal takes into account the size, dynamism, and
heterogeneity of the cloud when mapping VMs migrations, thus the proposal is developed in a distributed fashion, enabling the processing of each
cluster at a time. To evaluate the proposal, we used the Google cluster data set. Experiments demonstrate that the proposed technique can
improve the balance of allocated resources, thus helping reduce service degradation. Moreover, the runtime of the algorithm indicates that it is
feasible to be used in a real cloud computing environment with hundreds of physical servers and virtual machines.
Published in: Services (SERVICES), 2017 IEEE World Congress on
Date of Conference: 25-30 June 2017
Date Added to IEEE Xplore: 14 September 2017
ISBN Information:
INSPEC Accession Number: 17190566
DOI: 10.1109/SERVICES.2017.21
Publisher: IEEE
Conference Location: Honolulu, HI, USA
Contents
Download Citations
View References
Email
I. Introduction
Cloud Computing (CC) is a model that provides on-demand access to
computing resources [1]. Due to its advantages, CC usage has increased
over past years [2], [3]; thus the complexity and management costs of
cloud infrastructures also increase [4], [5].
Read document
Full Text
Abstract
Authors
Download PDF
Abstract Authors Figures References Citations Keywords Metrics Media
My Settings Get Help
Browse Subscribe
11/19/17, 7'56 PMImproving Cloud Computing Virtual Machines Balancing through Hosts and Virtual Machines Similarities - IEEE Conference Publication
Page 2 of 3http://ieeexplore.ieee.org/document/8036725/?reload=true
Print
Request Permissions
Alerts
Read document
Keywords
IEEE Keywords
Cloud computing, Proposals, Heuristic algorithms, Virtual machining,
Servers, Virtual machine monitors, Prediction algorithms
INSPEC: Controlled Indexing
cloud computing, computer centres, quality of service, resource
allocation, virtual machines
INSPEC: Non-Controlled Indexing
cloud computing virtual machines balancing, virtual machines similarities,
reduce service degradation, cloud computing environment, balance
techniques, physical hosts, management technique, quality of service,
VM migration mapping, cloud computing VM balancing algorithm, Google
cluster data set, resource allocation, physical servers
Author Keywords
cloud computing, virtual machines balance, cloud management,
autonomic cloud computing
Authors
Gabriel Beims Bräscher
Dept. of Informatic & Stat., Fed. Univ. of Santa
Catarina, Florianópolis, Brazil
Rafael Weingärtner
Carlos Becker Westphall
Dept. of Informatic & Stat., Fed. Univ. of Santa
Catarina, Florianópolis, Brazil
Related Articles
On aspect-orientation in distributed real-time dependable systems
A. Gal
Reconfiguration of resources in middleware
Figures
References
Citations
Keywords
Back to Top
Export to Collabratec
11/19/17, 7'56 PMImproving Cloud Computing Virtual Machines Balancing through Hosts and Virtual Machines Similarities - IEEE Conference Publication
Page 3 of 3http://ieeexplore.ieee.org/document/8036725/?reload=true
Reconfiguration of resources in middleware
H.A. Duran-Limon; G.S. Blair
A static timing analysis environment using Java architecture for safety
critical real-time systems
E.Y.-S. Hu; G. Bernat; A. Wellings
Configurable services for mobile users
A. Rasche; A. Polze
Performance evaluation of a probabilistic replica selection algorithm
S. Krishnamurthy; W.H. Sanders; M. Cukier
Handling FT-CORBA compliant interoperable object group references
R. Baldoni; C. Marchetti; R. Panella; L. Verde
Service differentiation of communication-bound processes in a real-time
operating system
D. Cotroneo; S. Russo; G. Ventre
Meta-programming techniques for distributed real-time and embedded
systems
J.K. Cross; D.C. Schmidt
Proceedings 35th Annual Simulation Symposium. SS 2002
A adaptive scheduler for QoS support in Compose|Q
S. Mohapatra; N. Venkatasubmanian
IEEE Account
»Change Username/Password
»Update Address
Purchase Details
»Payment Options
»Order History
»View Purchased Documents
Profile Information
»Communications Preferences
»Profession and Education
»Technical Interests
Need Help?
»US & Canada: +1 800 678 4333
»Worldwide: +1 732 981 0060
»Contact & Support
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2017 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.
About IEEE Xplore Contact Us
|Help
|Accessibility
|Terms of Use
|Nondiscrimination Policy
|Sitemap
|Privacy & Opting Out of Cookies
|
Article
Full-text available
The ever-growing intricacy and dynamicity of Cloud Computing Systems has created a need for Proactive Load Balancing which is an effective approach to improve the scalability of today’s Cloud services. In order to manage the load proactively on the Cloud system during application execution, load should be predicted through machine learning approaches and handled through VM migration approaches. Thus, this paper formulates an effort to focus on the research problem of designing a prediction-based approach for facilitating proactive load balancing through the prediction of multiple resource utilization parameters in Cloud. The involvement of this paper is twofold. Firstly, various machine learning approaches have been tested and compared for predicting host overutilization as well as underutilization. Secondly, the load prediction model having maximum accuracy from the tested models has been utilized for implementing the proactive VM migration using multiple resource utilization parameters. Further, the proposed technique has been validated through performance evaluation parameters using CloudSim and Weka toolkits. The simulation results clearly demonstrate that the proposed approach is effective for handling VM migration, reducing SLA Violations, VM migrations, execution mean and standard deviation time.
Conference Paper
Full-text available
It becomes a challenge to design an efficient load balancing method via live virtual machine (VM) migration without degrading application performance. Two major performance impacts on hosted applications that run on a VM are the system load balancing degree and the total time till a balanced state is reached. Existing load balancing methods usually ignore the VM migration time overhead. In contrast to sequential migration-based load balancing, this paper proposes using a network-topology aware parallel migration to speed up the load balancing process in a data center. We transform the VM migration-based multi-resource load-balancing problem into a minimum weighted matching problem over a weighted bipartite graph. By obtaining the minimum weighted matching pairs through the Hungarian method, we parallel migrate multiple VMs from overloaded hosts to underutilized hosts to reduce the time it takes to reach a load balanced state. The experimental results show that our algorithm not only obtains a compatible multi-resource load balancing performance but also improves the balanced time which results in at most a 10% throughput gain by assuming a large batch application running on all VMs.
Conference Paper
Full-text available
Data center optimization, mainly through virtual machine (VM) placement, has received considerable attention in the past years. A lot of heuristics have been proposed to give quick and reasonably good solutions to this problem. However it is difficult to compare them as they use different datasets, while the distribution of resources in the datasets has a big impact on the results. In this paper we propose the first benchmark for VM placement heuristics and we define a novel heuristic. Our benchmark is inspired from a real data center and explores different possible demographics of data centers, which makes it suitable when comparing the behaviour of heuristics. Our new algorithm, RBP, outperforms the state-of-the-art heuristics and provides close to optimal results quickly.
Conference Paper
Full-text available
Given cloud-based realization of a distributed system S, QoS auditing enables risk analysis and accounting of SLA violations under various security threats and resource depletions faced by S. The problem of QoS failures and security infringements arises due to the third-party control of cloud resources and components that are used in realizing the application-oriented service exported by S. The less-than-100% trust between the various sub-systems of S is a major issue that necessitates a probabilistic analysis of the application behavior relative to the SLA negotiated with S. In this light, QoS auditing allows reasoning about how good the SLA is complied by S in the face of hostile environment conditions. The paper describes case studies of CDN and replicated web service realized on a cloud.
Conference Paper
Abstract—Due to constant workload growth, the infrastructure used to support cloud computing (CC) environments increases in size and complexity. As a consequence of that, human administrators are not able to monitor, analyze, plan and execute actions upon the environment, seeking goals such as the environment optimization and service level agreements fulfillment. This proposal provides an autonomic framework to create virtual machines migrations and heuristics to select hosts to be activated or deactivated when needed. Moreover, the framework proposed in this paper works in a distributed way using multi-agent systems concepts. We provide an architecture to deal with the size, heterogeneity and dynamism of CC environments. Further, our proposal was added to the CloudStack platform as a plug-in for validation and experimentation. Keywords-Cloud computing orchestration; autonomic management framework.
Article
Load management in Cloud data centers must take into account 1) hardware diversity of hosts, 2) heterogeneous user requirements, 3) volatile resource usage profiles of virtual machines (VMs), 4) fluctuating load patterns, and 5) energy consumption. This work proposes distributed problem solving techniques for load management in data centers supported by VM live migration. Collaborative agents are endowed with a load balancing protocol and an energy-aware consolidation protocol to balance and consolidate heterogeneous loads in a distributed manner while reducing energy consumption costs. Agents are provided with 1) policies for deciding when to migrate VMs, 2) a set of heuristics for selecting the VMs to be migrated, 3) a set of host selection heuristics for determining where to migrate VMs, and 4) policies for determining when to turn off/on hosts. This paper also proposes a novel load balancing heuristic that migrates the VMs causing the largest resource usage imbalance from overloaded hosts to underutilized hosts whose resource usage imbalances are reduced the most by hosting the VMs. Empirical results show that agents adopting the distributed problem solving techniques are efficient and effective in balancing data centers, consolidating heterogeneous loads, and carrying out energy-aware server consolidation.
Article
With the rise of cloud computing, a huge complexity growth of the structure that is the base of the Cloud happens. Thus, to effectively manage applications and resources it is crucial the use of models and tools that create an application profile which is used to apply forecasting models to determine the most suitable amount of resource for each workload. There are models and tools that address the creation of an application profile to later apply some forecasting technique and estimate the amount of resource needed for a workload. Therefore, this article aims to present a taxonomy for application profiling models and tools, presenting its main characteristics, challenges, describing and comparing such models and tool. At the end this work presents a discussion about the use of application profiling and its future research trends.