Auto-scaling a video-conference platform with Reinforcement learning

One of the capabilities that video-conferencing platforms are expected to have, as well as other distributed services, is being able to scale horizontally. This is because workload is not constant in a lot of applications, so setting a fixed number of servers beforehand will probably end up with eit...

Descripción completa

Detalles Bibliográficos
Autor: Roy Campderrós, Francesc
Tipo de recurso: tesis de maestría
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/360547
Acceso en línea:https://hdl.handle.net/2117/360547
Access Level:acceso abierto
Palabra clave:Reinforcement learning
Teleconferencees
Auto-scaling
Video-conference
Aprenentatge per reforç
Teleconferències
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
id ES_22e1c31eb3f20156d3f1bc7e5bfcd266
oai_identifier_str oai:upcommons.upc.edu:2117/360547
network_acronym_str ES
network_name_str España
repository_id_str
spelling Auto-scaling a video-conference platform with Reinforcement learningRoy Campderrós, FrancescReinforcement learningTeleconferenceesAuto-scalingVideo-conferenceReinforcement learningAuto-scalingVideo-conferenceReinforcement learningAprenentatge per reforçTeleconferènciesÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàticOne of the capabilities that video-conferencing platforms are expected to have, as well as other distributed services, is being able to scale horizontally. This is because workload is not constant in a lot of applications, so setting a fixed number of servers beforehand will probably end up with either bad quality of service when load is too high, or resources wasted when load is too low. From the service providers's point of view both situations are undesirable. On the one side, they may be penalised when not delivering sufficient quality of service to their users. On the other side, having servers infra-used is inefficient, as more servers running imply higher electricity/renting costs. Therefore this auto-scaling capability is crucial in order to optimize the expenses at the end of the month. In this work we develop an auto-scaling algorithm based on Reinforcement learning (RL) to be applied to the adjustment of computing capacity of a distributed video-conference platform such as Jitsi and perform a comparison with simple threshold based methods (TBM), which are offered by many cloud providers as the default auto-scaling service. We perform this comparison under different synthetic workload patterns. Since video-conferencing platforms consume a lot of computing resources and we want to analyse different high loads, the comparison is done with simulations. We demonstrate that RL performs better than TBM in all the scenarios evaluated in terms of money expended (with different patterns tested) and that the difference between them is accentuated the more complex the workload pattern is.Universitat Politècnica de CatalunyaNavarro Moldes, LeandroFreitag, Fèlix20212021-10-1820222022-01-24master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/360547reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3605472026-05-27T15:37:01Z
dc.title.none.fl_str_mv Auto-scaling a video-conference platform with Reinforcement learning
title Auto-scaling a video-conference platform with Reinforcement learning
spellingShingle Auto-scaling a video-conference platform with Reinforcement learning
Roy Campderrós, Francesc
Reinforcement learning
Teleconferencees
Auto-scaling
Video-conference
Reinforcement learning
Auto-scaling
Video-conference
Reinforcement learning
Aprenentatge per reforç
Teleconferències
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
title_short Auto-scaling a video-conference platform with Reinforcement learning
title_full Auto-scaling a video-conference platform with Reinforcement learning
title_fullStr Auto-scaling a video-conference platform with Reinforcement learning
title_full_unstemmed Auto-scaling a video-conference platform with Reinforcement learning
title_sort Auto-scaling a video-conference platform with Reinforcement learning
dc.creator.none.fl_str_mv Roy Campderrós, Francesc
author Roy Campderrós, Francesc
author_facet Roy Campderrós, Francesc
author_role author
dc.contributor.none.fl_str_mv Navarro Moldes, Leandro
Freitag, Fèlix
dc.subject.none.fl_str_mv Reinforcement learning
Teleconferencees
Auto-scaling
Video-conference
Reinforcement learning
Auto-scaling
Video-conference
Reinforcement learning
Aprenentatge per reforç
Teleconferències
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
topic Reinforcement learning
Teleconferencees
Auto-scaling
Video-conference
Reinforcement learning
Auto-scaling
Video-conference
Reinforcement learning
Aprenentatge per reforç
Teleconferències
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
description One of the capabilities that video-conferencing platforms are expected to have, as well as other distributed services, is being able to scale horizontally. This is because workload is not constant in a lot of applications, so setting a fixed number of servers beforehand will probably end up with either bad quality of service when load is too high, or resources wasted when load is too low. From the service providers's point of view both situations are undesirable. On the one side, they may be penalised when not delivering sufficient quality of service to their users. On the other side, having servers infra-used is inefficient, as more servers running imply higher electricity/renting costs. Therefore this auto-scaling capability is crucial in order to optimize the expenses at the end of the month. In this work we develop an auto-scaling algorithm based on Reinforcement learning (RL) to be applied to the adjustment of computing capacity of a distributed video-conference platform such as Jitsi and perform a comparison with simple threshold based methods (TBM), which are offered by many cloud providers as the default auto-scaling service. We perform this comparison under different synthetic workload patterns. Since video-conferencing platforms consume a lot of computing resources and we want to analyse different high loads, the comparison is done with simulations. We demonstrate that RL performs better than TBM in all the scenarios evaluated in terms of money expended (with different patterns tested) and that the difference between them is accentuated the more complex the workload pattern is.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-10-18
2022
2022-01-24
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/360547
url https://hdl.handle.net/2117/360547
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869404607420039168
score 15,300724

Similares en LA Referencia