Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Cost-Efficient Resource Scheduling under QoS Constraints for Geo-Distributed Data Centers
Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013). (Distributed Systems and Communications Research Group (DISCO))ORCID-id: 0000-0002-6221-3875
(University of Missouri--Kansas City, USA.)
Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013), Institutionen för matematik och datavetenskap (from 2013).
(University of Missouri--Kansas City, USA.)
2018 (Engelska)Ingår i: NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium, IEEE, 2018Konferensbidrag (Refereegranskat)
Abstract [en]

Geo-distributed Data Centers (DCs) are more and more common in order to provide scalability for the ever increasing compute demands of modern applications. When multiple distributed DCs can serve user requests, it is important to determine, which DC and server to select to fulfil the compute request, given that enough resources are available in terms of CPU and bandwidth. The problem is complicated as every DC has different operational costs associated, such as energy costs, carbon emission cost and bandwidth costs. In this paper, we develop a novel mathematical optimization model that guides the decision maker which DC to select, which server to use to host the compute demands and which DC gateway and network path to use to route the network traffic in order to satisfy the compute, bandwidth and latency demands. Our model includes the queuing delay depending on the traffic load in the model. Our extensive numerical evaluation based on real-world DC locations, demand patterns and resource provision costs shows how operational cost increases with traffic load, and we analyse the impact of different latency bounds on the performance of different virtual networks.

Ort, förlag, år, upplaga, sidor
IEEE, 2018.
Nationell ämneskategori
Kommunikationssystem
Forskningsämne
Datavetenskap
Identifikatorer
URN: urn:nbn:se:kau:diva-48481DOI: 10.1109/NOMS.2018.8406272ISBN: 978-1-5386-3417-2 (tryckt)ISBN: 978-1-5386-3416-5 (digital)OAI: oai:DiVA.org:kau-48481DiVA, id: diva2:1092851
Konferens
IEEE/IFIP Network Operations and Management Symposium (NOMS 2018), 23-27 April 2018, Taipei, Taiwan.
Projekt
READYHITS, 4707
Forskningsfinansiär
KK-stiftelsen
Anmärkning

Konferensbidraget ingick i avhandlingen som manuskript

Tillgänglig från: 2017-05-04 Skapad: 2017-05-04 Senast uppdaterad: 2019-11-11Bibliografiskt granskad
Ingår i avhandling
1. Cost- and Performance-Aware Resource Management in Cloud Infrastructures
Öppna denna publikation i ny flik eller fönster >>Cost- and Performance-Aware Resource Management in Cloud Infrastructures
2017 (Engelska)Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

High availability, cost effectiveness and ease of application deployment have accelerated the adoption rate of cloud computing. This fast proliferation of cloud computing promotes the rapid development of large-scale infrastructures. However, large cloud datacenters (DCs) require infrastructure, design, deployment, scalability and reliability and need better management techniques to achieve sustainable design benefits. Resources inside cloud infrastructures often operate at low utilization, rarely exceeding 20-30%, which increases the operational cost significantly, especially due to energy consumption. To reduce operational cost without affecting quality of service (QoS) requirements, cloud applications should be allocated just enough resources to minimize their completion time or to maximize utilization. 

The focus of this thesis is to enable resource-efficient and performance-aware cloud infrastructures by addressing above mentioned cost and performance related challenges. In particular, we propose algorithms, techniques, and deployment strategies for improving the dynamic allocation of virtual machines (VMs) into physical machines (PMs). 

For minimizing the operational cost, we mainly focus on optimizing energy consumption of PMs by applying dynamic VM consolidation methods. To make VM consolidation techniques more efficient, we propose to utilize multiple paths to spread traffic and deploy recent queue management schemes which can maximize network resource utilization and reduce both downtime and migration time for live migration techniques. In addition, a dynamic resource allocation scheme is presented to distribute workloads among geographically dispersed DCs considering their location based time varying costs due to e.g. carbon emission or bandwidth provision. For optimizing performance level objectives, we focus on interference among applications contending in shared resources and propose a novel VM consolidation scheme considering sensitivity of the VMs to their demanded resources. Further, to investigate the impact of uncertain parameters on cloud resource allocation and applications’ QoS such as unpredictable variations in demand, we develop an optimization model based on the theory of robust optimization. Furthermore, in order to handle the scalability issues in the context of large scale infrastructures, a robust and fast Tabu Search algorithm is designed and evaluated.

Abstract [en]

High availability, cost effectiveness and ease of application deployment have accelerated the adoption rate of cloud computing. This fast proliferation of cloud computing promotes the rapid development of large-scale infrastructures. However, large cloud datacenters (DCs) require infrastructure, design, deployment, scalability and reliability and need better management techniques to achieve sustainable design benefits. Resources inside cloud infrastructures often operate at low utilization, rarely exceeding 20-30%, which increases the operational cost significantly, especially due to energy consumption. To reduce operational cost without affecting quality of service (QoS) requirements, cloud applications should be allocated just enough resources to minimize their completion time or to maximize utilization. 

The focus of this thesis is to enable resource-efficient and performance-aware cloud infrastructures by addressing above mentioned cost and performance related challenges. In particular, we propose algorithms, techniques, and deployment strategies for improving the dynamic allocation of virtual machines (VMs) into physical machines (PMs).

Ort, förlag, år, upplaga, sidor
Karlstad: Karlstads universitet, 2017. s. 252
Serie
Karlstad University Studies, ISSN 1403-8099 ; 2017:21
Nyckelord
Cloud Computing, OpenStack, Robust Optimization, Latency, Tabu Search, Resource Management, Resource Contention, QoS
Nationell ämneskategori
Kommunikationssystem
Forskningsämne
Datavetenskap
Identifikatorer
urn:nbn:se:kau:diva-48482 (URN)978-91-7063-783-4 (ISBN)978-91-7063-784-1 (ISBN)
Disputation
2017-06-21, 21A342 (Eva Erikssonsalen), Universitetsgatan 2, 651 88 Karlstad, Karlstad, 10:30 (Engelska)
Opponent
Handledare
Projekt
HITS, 4707
Forskningsfinansiär
KK-stiftelsen
Anmärkning

Paper 8 "Robust optimization for energy-efficient virtual machine consolidation in modern datacenters" ingick i avhandlingen som manuskript, nu publicerad. 

Paper 5 "Cost- and Performance-Aware Resource Management in Cloud Infrastructures" ingick i avhandlingen som manuskript nu konferensbidrag

Tillgänglig från: 2017-05-19 Skapad: 2017-05-04 Senast uppdaterad: 2019-11-07Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Personposter BETA

Nasim, Robayet

Sök vidare i DiVA

Av författaren/redaktören
Nasim, Robayet
Av organisationen
Institutionen för matematik och datavetenskap (from 2013)
Kommunikationssystem

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 675 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf