QoE-aware auto-scaling of heterogeneous containerized services (and its application to health services)

Guilherme Santos, Hervé Paulino, Tomé Vardasca

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Containerized service is currently a widely adopted solution to deploy services in the cloud. However, many companies offer a very diverse set of Web accessible services that are subjected to very distinctive workloads. Consequently, to correctly provision the right amount of resources for each of these services is a challenge. In this paper we propose the Autonomic ConTainerized Service Scaler (ACTS), an autonomic system able to horizontally and vertically scale a set of heterogeneous containerized services subjected to different workloads. The adaptation decisions depended on a set of high-level Quality of Experience (QoE) metrics centered on the services' end-user. We have applied ACTS to some of the digital services of the Shared Services of the Ministry of Health (SPMS) public company. The experimental results show that our solution is able to adequately adapt the configuration of each service, as a direct response to alterations on its workload.

Original languageEnglish
Title of host publication35th Annual ACM Symposium on Applied Computing, SAC 2020
PublisherAssociation for Computing Machinery
Pages242-249
Number of pages8
ISBN (Electronic)9781450368667
DOIs
Publication statusPublished - 30 Mar 2020
Event35th Annual ACM Symposium on Applied Computing, SAC 2020 - Brno, Czech Republic
Duration: 30 Mar 20203 Apr 2020

Publication series

NameProceedings of the ACM Symposium on Applied Computing
PublisherAssociation for Computing Machinery

Conference

Conference35th Annual ACM Symposium on Applied Computing, SAC 2020
CountryCzech Republic
CityBrno
Period30/03/203/04/20

Keywords

  • Auto-scaling
  • Containers
  • Health care
  • Quality of experience

Fingerprint Dive into the research topics of 'QoE-aware auto-scaling of heterogeneous containerized services (and its application to health services)'. Together they form a unique fingerprint.

Cite this