umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Multivariate LSTM-Based Location-Aware Workload Prediction for Edge Data Centers
Umeå University, Faculty of Science and Technology, Department of Computing Science. (Distributed Systems)ORCID iD: 0000-0002-9156-3364
Umeå University, Faculty of Science and Technology, Department of Computing Science. (Distributed Systems)ORCID iD: 0000-0003-0106-3049
Umeå University, Faculty of Science and Technology, Department of Computing Science. (Distributed Systems)
2019 (English)In: Proceedings, 19th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, IEEE, 2019, p. 341-350Conference paper, Published paper (Refereed)
Abstract [en]

Mobile Edge Clouds (MECs) is a promising computing platform to overcome challenges for the success of bandwidth-hungry, latency-critical applications by distributing computing and storage capacity in the edge of the network as Edge Data Centers (EDCs) within the close vicinity of end-users. Due to the heterogeneous distributed resource capacity in EDCs, the application deployment flexibility coupled with the user mobility, MECs bring significant challenges to control resource allocation and provisioning. In order to develop a self-managed system for MECs which efficiently decides how much and when to activate scaling, where to place and migrate services, it is crucial to predict its workload characteristics, including variations over time and locality. To this end, we present a novel location-aware workload predictor for EDCs. Our approach leverages the correlation among workloads of EDCs in a close physical distance and applies multivariate Long Short-Term Memory network to achieve on-line workload predictions for each EDC. The experiments with two real mobility traces show that our proposed approach can achieve better prediction accuracy than a state-of-the art location-unaware method (up to 44%) and a location-aware method (up to 17%). Further, through an intensive performance measurement using various input shaking methods, we substantiate that the proposed approach achieves a reliable and consistent performance.

Place, publisher, year, edition, pages
IEEE, 2019. p. 341-350
Keywords [en]
Mobile Edge Cloud, Edge Data Center, ResourceManagement, Workload Prediction, Location-aware, MachineLearning
National Category
Computer Systems
Research subject
Computer Systems
Identifiers
URN: urn:nbn:se:umu:diva-159540DOI: 10.1109/CCGRID.2019.00048ISI: 000483058700039Scopus ID: 2-s2.0-85069517887ISBN: 978-1-7281-0912-1 (electronic)ISBN: 978-1-7281-0913-8 (print)OAI: oai:DiVA.org:umu-159540DiVA, id: diva2:1319229
Conference
CCGrid 2019, 19th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (IEEE/ACM CCGrid 2019), 14-17 May, Larnaca, Cyprus
Available from: 2019-05-30 Created: 2019-05-30 Last updated: 2019-09-27Bibliographically approved
In thesis
1. Autonomous resource management for Mobile Edge Clouds
Open this publication in new window or tab >>Autonomous resource management for Mobile Edge Clouds
2019 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Mobile Edge Clouds (MECs) are platforms that complement today's centralized clouds by distributing computing and storage capacity across the edge of the network, in Edge Data Centers (EDCs) located in close proximity to end-users. They are particularly attractive because of their potential benefits for the delivery of bandwidth-hungry, latency-critical applications. However, the control of resource allocation and provisioning in MECs is challenging because of the  heterogeneous distributed resource capacity of EDCs as well as the need for flexibility in application deployment and the dynamic nature of mobile users. To realize the potential of MECs, efficient resource management systems that can deal with these challenges must be designed and built.

This thesis focuses on two problems. The first relates to the fact that it is unrealistic to expect MECs to become successful based solely on MEC-native applications. Thus, to spur the development of MECs, we investigated the benefits MECs can offer to non-MEC-native applications, i.e., applications not specifically engineered for MECs. One class of popular applications that may benefit strongly from deployment on MECs are cloud-native applications, particularly microservice-based applications with high deployment flexibility. We therefore quantified the performance of cloud-native applications deployed using resources from both cloud datacenters and edge locations. We also developed a network communication profiling tool to identify the aspects of these applications that reduce the benefits they derive from deployment on MECs, and proposed design improvements that would allow such applications to better exploit MECs' capabilities.

The second problem examined in this thesis relates to the dynamic nature of resource demand in MECs. To overcome the challenges arising from this dynamicity, we make use of statistical time series models and machine learning techniques to develop two workload prediction models for EDCs that account for both user mobility and the correlation of workload changes among EDCs in close physical proximity.  

Place, publisher, year, edition, pages
Umeå: Institutionen för datavetenskap, Umeå universitet, 2019. p. 31
Series
Report / UMINF, ISSN 0348-0542 ; 19.07
National Category
Computer Sciences
Identifiers
urn:nbn:se:umu:diva-162924 (URN)9789178551163 (ISBN)
Presentation
2019-09-19, MA121, MIT building, Umeå University, Umeå, 13:15
Opponent
Supervisors
Available from: 2019-09-02 Created: 2019-09-02 Last updated: 2019-09-02Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Nguyen, ChanhKlein, CristianElmroth, Erik

Search in DiVA

By author/editor
Nguyen, ChanhKlein, CristianElmroth, Erik
By organisation
Department of Computing Science
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 638 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf