umu.sePublikationer
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
Location-aware load prediction in edge data centers
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. (Distributed Systems)ORCID-id: 0000-0002-9156-3364
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. (Distributed Systems)
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. (Distributed Systems)
2017 (Engelska)Ingår i: 2017 Second International Conference on Fog and Mobile Edge Computing (FMEC), IEEE, 2017, s. 25-31Konferensbidrag, Publicerat paper (Övrigt vetenskapligt)
Abstract [en]

Mobile Edge Cloud (MEC) is a platform complementing traditional centralized clouds, consisting in moving computing and storage capacity closer to users -e. g., as Edge Data Centers (EDC) in base stations -in order to reduce application-level latency and network bandwidth. The bounded coverage radius of base station and limited capacity of each EDC intertwined with user mobility challenge the operator's ability to perform capacity adjustment and planning. To face this challenge, proactive resource provisioning can be performed. The resource usage in each EDC is estimated in advance, which is made available for the decision making to efficiently determine various management actions and ensure that EDCs persistently satisfies the Quality of Service (QoS), while maximizing resource utilization. In this paper, we propose location-aware load prediction. For each EDC, load is not only predicted using its own historical load time series -as done for centralized clouds -but also those of its neighbor EDCs. We employ Vector Autoregression Model (VAR) in which the correlation among adjacent EDCs load time series are exploited. We evaluate our approach using real world mobility traces to simulate load in each EDC and conduct various experiments to evaluate the proposed algorithm. Result shows that our proposed algorithm is able to achieve an average accuracy of up to 93% on EDCs with substantial average load, which slightly improves prediction by 4.3% compared to the state-of-the-art approach. Considering the expected scale of MEC, this translates to substantial cost savings e. g., servers can be shutdown without QoS violation.

Ort, förlag, år, upplaga, sidor
IEEE, 2017. s. 25-31
Nyckelord [en]
Workload Prediction, Proactive Resource Management, Mobile Edge Cloud, VAR Model, User Mobility
Nationell ämneskategori
Datorsystem
Identifikatorer
URN: urn:nbn:se:umu:diva-135700ISI: 000411731700004ISBN: 978-1-5386-2859-1 (tryckt)OAI: oai:DiVA.org:umu-135700DiVA, id: diva2:1105213
Konferens
The 2nd International Conference on Fog and Mobile Edge Computing (FMEC), May 8-11, 2017, Valencia, Spain
Projekt
WASPTillgänglig från: 2017-06-02 Skapad: 2017-06-02 Senast uppdaterad: 2019-09-02Bibliografiskt granskad
Ingår i avhandling
1. Autonomous resource management for Mobile Edge Clouds
Öppna denna publikation i ny flik eller fönster >>Autonomous resource management for Mobile Edge Clouds
2019 (Engelska)Licentiatavhandling, sammanläggning (Övrigt vetenskapligt)
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.  

Ort, förlag, år, upplaga, sidor
Umeå: Institutionen för datavetenskap, Umeå universitet, 2019. s. 31
Serie
Report / UMINF, ISSN 0348-0542 ; 19.07
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
urn:nbn:se:umu:diva-162924 (URN)9789178551163 (ISBN)
Presentation
2019-09-19, MA121, MIT building, Umeå University, Umeå, 13:15
Opponent
Handledare
Tillgänglig från: 2019-09-02 Skapad: 2019-09-02 Senast uppdaterad: 2019-09-02Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Personposter BETA

Nguyen, Chanh Le TanKlein, CristianElmroth, Erik

Sök vidare i DiVA

Av författaren/redaktören
Nguyen, Chanh Le TanKlein, CristianElmroth, Erik
Av organisationen
Institutionen för datavetenskap
Datorsystem

Sök vidare utanför DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetricpoäng

isbn
urn-nbn
Totalt: 443 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