End-to-End Performance Prediction for Selecting Cloud Services Solutions

Karim, Raed; Miri, Ali

doi:10.1109/sose.2015.11

Cited by 6 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prior works have focused on how to save energy, improve performance and increase profit and so on [57]. In this subsection, the most recent prediction techniques, especially ML techniques, applied in the field of VM consolidation based energy consumption, will be reviewed.…”

Section: Prediction Processmentioning

confidence: 99%

An Energy-Aware Real-Time VM-Provisioning Framework For Heterogeneous Data Centres

Ismaeel¹

2021

Preprint

View full text Add to dashboard Cite

<div>Increasing power efficiency is one of the most important operational factors for any data centre providers. In this context, one of the most useful approaches is to reduce the number of utilized Physical Machines (PMs) through optimal distribution and re-allocation of Virtual Machines (VMs) without affecting the Quality of Service (QoS). Dynamic VMs provisioning makes use of monitoring tools, historical data, prediction techniques, as well as placement algorithms to improve VMs allocation and migration. Consequently, the efficiency of the data centre energy consumption increases.</div><div>In this thesis, we propose an efficient real-time dynamic provisioning framework to reduce energy in heterogeneous data centres. This framework consists of an efficient workload preprocessing, systematic VMs clustering, a multivariate prediction, and an optimal Virtual Machine Placement (VMP) algorithm. Additionally, it takes into consideration VM and user behaviours along with the existing state of PMs. The proposed framework consists of a pipeline successive subsystems. These subsystems could be used separately or combined to improve accuracy, efficiency, and speed of workload clustering, prediction and provisioning purposes.<br></div><div>The pre-processing and clustering subsystems uses current state and historical workload data to create efficient VMs clusters. Efficient VMs clustering include less consumption resources, faster computing and improved accuracy. A modified multivariate Extreme Learning Machine (ELM)-based predictor is used to forecast the number of VMs in each cluster for the subsequent period. The prediction subsystem takes users’ behaviour into consideration to exclude unpredictable VMs requests.<br></div><div>The placement subsystem is a multi-objective placement algorithm based on a novel Machine Condition Index (MCI). MCI represents a group of weighted components that is inclusive of data centre network, PMs, storage, power system and facilities used in any data centre. In this study it will be used to measure the extent to which PM is deemed suitable for handling the new and/or consolidated VM in large scale heterogeneous data centres. It is an efficient tool for comparing server energy consumption used to augment the efficiency and manageability of data centre resources.</div><div> The proposed framework components separately are tested and evaluated with both synthetic and realistic data traces. Simulation results show that proposed subsystems can achieve efficient results as compared to existing algorithms. <br></div>

show abstract

Section: Prediction Processmentioning

confidence: 99%

An Energy-Aware Real-Time VM-Provisioning Framework For Heterogeneous Data Centres

Ismaeel¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Many performance prediction algorithms and tools have been developed, which can be applied to predict the future CPU, memory load, VMs, etc. [97].…”

Section: Workload Prediction Subsystemmentioning

confidence: 99%

“…In recent years, many performance prediction algorithms and tools have been developed, which can be applied to predict the future CPU, memory load, VMs ... etc. Their focuses were on how to save energy, improve performance and increase profit and so on [97]. In next subsections, the most recent prediction techniques, especially ML techniques, applied in the field of VM consolidation based energy consumption will be reviewed.…”

Section: Prediction Processmentioning

confidence: 99%

See 1 more Smart Citation

Proactive dynamic virtual-machine consolidation for energy conservation in cloud data centres

2018

Self Cite

View full text Add to dashboard Cite

Data center power consumption is among the largest commodity expenditures for many organizations. Reduction of power used in cloud data centres with heterogeneous physical resources can be achieved through Virtual-Machine (VM) consolidation which reduces the number of Physical Machines (PMs) used, subject to Quality of Service (QoS) constraints. This paper provides an in-depth survey of the most recent techniques and algorithms used in proactive dynamic VM consolidation focused on energy consumption. We present a general framework that can be used on multiple phases of a complete consolidation process.

show abstract

“…We use the new set of similar composite services in the incorporated Local Regularization Term of the tensor R to predict end-to-end QoS values. In this thesis (see also[99]), we proposed to use historical QoS data of cloud composite services by measuring the correlation of their component services in order to predict unknown end-to-end QoS values of target cloud composite services. The basic idea is that if two cloud component services share the same experiences (they have similar QoS values) when they were combined (separately) with other components (from other service type) and invoked in the past, they are more likelyto have similar experiences when they are combined with a certain component in the future.…”

mentioning

confidence: 99%

End-to-end QoS computation for vertical service composition in the cloud

Karim¹

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Cloud services are designed to provide users with different computing models such as software-as-a-Services (SaaS), Infrastructure-as-a-Service (IaaS), Data-as-a-Service (DaaS), and other IT related services (denoted as XaaS). Easy, scalable and on-demand cloud services are offered by cloud providers to users. With the prevalence of different types of cloud services, the task of selecting the best cloud service solution has become more and more challenging. Cloud service solutions are offered through a collaboration of different cloud services at different cloud layers. This type of collaborations is denoted as vertical service composition. Quality of Service (QoS) properties are used as differentiating factors for selecting the best services among functionally equivalent services. In this thesis, we introduce a new service selection framework for the cloud which vertically matches services offered by different cloud providers based on users’ end-to-end QoS requirements. Functional requirements can be satisfied by the required cloud service (software service, platform service, etc) alone. However, users’ QoS requirements must be satisfied using all involved cloud services in a service composition. Therefore, in order to select the best cloud service compositions for users, QoS values of these compositions must be end-to-end. To tackle the problem of computing unknown end-to-end QoS values of vertical cloud service compositions for target users (for whom these values are computed), we propose two strategies: QoS mapping and aggregation and QoS prediction. The former deals with new cloud service compositions with no prior history. Using this strategy, we can map users’ QoS requirements onto different cloud layers and then we aggregate QoS values guaranteed by cloud providers to estimate end-to-end QoS values. The latter deals with cloud service compositions for which QoS data have been recorded in an active system. Using the QoS prediction strategy, we utilize historical QoS data of previously invoked service compositions and other service and user information to predict end-to-end QoS values. The presented experimental results demonstrate the importance of considering vertically composed cloud services when computing end-to-end QoS values as opposed to traditional prediction approaches. Our QoS prediction approach outperforms other prediction approaches in terms of the prediction accuracy by at least 20%.

show abstract

End-to-End Performance Prediction for Selecting Cloud Services Solutions

Cited by 6 publications

References 14 publications

An Energy-Aware Real-Time VM-Provisioning Framework For Heterogeneous Data Centres

An Energy-Aware Real-Time VM-Provisioning Framework For Heterogeneous Data Centres

Proactive dynamic virtual-machine consolidation for energy conservation in cloud data centres

End-to-end QoS computation for vertical service composition in the cloud

Contact Info

Product

Resources

About