DeepBGP: A Machine Learning Solution to reduce BGP Routing Convergence Time by Fine-Tuning MRAI
Ano de defesa: | 2019 |
---|---|
Autor(a) principal: | |
Outros Autores: | |
Orientador(a): | |
Banca de defesa: | |
Tipo de documento: | Tese |
Tipo de acesso: | Acesso aberto |
Idioma: | eng |
Instituição de defesa: |
Universidade Federal do Amazonas
Instituto de Computação Brasil UFAM Programa de Pós-graduação em Informática |
Programa de Pós-Graduação: |
Não Informado pela instituição
|
Departamento: |
Não Informado pela instituição
|
País: |
Não Informado pela instituição
|
Palavras-chave em Português: | |
Link de acesso: | https://tede.ufam.edu.br/handle/tede/7697 |
Resumo: | The organization of the Internet is composed of administrative domains, known as Autonomous Systems (ASes), that exchange reachability information by means of the Border Gateway Protocol (BGP). Since a high convergence delay leads to packet losses and service unavailability, such a protocol has to converge as fast as possible. As this can happen due to BGP's own mechanism of UPDATE messages, that produces a humongous amount of messages, BGP reduces the number of UPDATEs exchanged between two BGP routers by holding consecutive announcements from a router to a neighbor for a given amount of time. The BGP timer responsible for this task is called Minimum Route Advertisement Interval (MRAI), which has an important impact in routing convergence. The Software-Defined Networking (SDN) paradigm can be used to leverage interdomain routing services performance via the logically centralized controlling benefits of intradomain settings. SDN principles has been successfully deployed in data centers, LANs, and in several other studies, where each each AS is modeled with a logically centralized routing control, offering new opportunities and bringing BGP routing convergence improvements. In this work, an extensive survey is presented on the state-of-the-art about research efforts to achieve better BGP routing convergence time. Furthermore, I pinpoint the open issues in this research field and propose DeepBGP, to the best of my knowledge, the first hybrid framework endowed with a learning mechanism, that integrates the SDN paradigm within interdomain routing domains, to improve the interdomain routing convergence time. This is achieved by employing the LSTM learning technique that allows the tuning of MRAI value aiming to reduce the convergence time according to learned patterns from collected BGP UPDATE features. The PEERING platform was used to provide a real scenario that allows the sending of announcements to the Internet. With the benefits of having such an actual testbed I carried out experiments with protocol characteristics that can impact the routing convergence. The experimental results show that the adaptive MRAI in the DeepBGP framework is able to reduce the BGP routing convergence time when compared to the use of static MRAIs. |
id |
UFAM_31588b067f2aa46a3c067cdff956d4ae |
---|---|
oai_identifier_str |
oai:https://tede.ufam.edu.br/handle/:tede/7697 |
network_acronym_str |
UFAM |
network_name_str |
Biblioteca Digital de Teses e Dissertações da UFAM |
repository_id_str |
|
spelling |
DeepBGP: A Machine Learning Solution to reduce BGP Routing Convergence Time by Fine-Tuning MRAIA Machine-Learning Solution to reduce BGP Routing Convergence Time in a Hybrid SDN-Interdomain environment by Fine-Tuning MRAIGerenciamento de redesRoteamento entre domíniosTempo de convergênciaBorder Gateway ProtocolLong Short-Term MemoryLong Short-Term MemoryCIÊNCIAS EXATAS E DA TERRA: CIÊNCIA DA COMPUTAÇÃO: SISTEMAS DE COMPUTAÇÃObgpconvergence timelstmnetwork managementinterdomain routingThe organization of the Internet is composed of administrative domains, known as Autonomous Systems (ASes), that exchange reachability information by means of the Border Gateway Protocol (BGP). Since a high convergence delay leads to packet losses and service unavailability, such a protocol has to converge as fast as possible. As this can happen due to BGP's own mechanism of UPDATE messages, that produces a humongous amount of messages, BGP reduces the number of UPDATEs exchanged between two BGP routers by holding consecutive announcements from a router to a neighbor for a given amount of time. The BGP timer responsible for this task is called Minimum Route Advertisement Interval (MRAI), which has an important impact in routing convergence. The Software-Defined Networking (SDN) paradigm can be used to leverage interdomain routing services performance via the logically centralized controlling benefits of intradomain settings. SDN principles has been successfully deployed in data centers, LANs, and in several other studies, where each each AS is modeled with a logically centralized routing control, offering new opportunities and bringing BGP routing convergence improvements. In this work, an extensive survey is presented on the state-of-the-art about research efforts to achieve better BGP routing convergence time. Furthermore, I pinpoint the open issues in this research field and propose DeepBGP, to the best of my knowledge, the first hybrid framework endowed with a learning mechanism, that integrates the SDN paradigm within interdomain routing domains, to improve the interdomain routing convergence time. This is achieved by employing the LSTM learning technique that allows the tuning of MRAI value aiming to reduce the convergence time according to learned patterns from collected BGP UPDATE features. The PEERING platform was used to provide a real scenario that allows the sending of announcements to the Internet. With the benefits of having such an actual testbed I carried out experiments with protocol characteristics that can impact the routing convergence. The experimental results show that the adaptive MRAI in the DeepBGP framework is able to reduce the BGP routing convergence time when compared to the use of static MRAIs.The organization of the Internet is composed of administrative domains, known as Autonomous Systems (ASes), that exchange reachability information by means of the Border Gateway Protocol (BGP). Since a high convergence delay leads to packet losses and service unavailability, such a protocol has to converge as fast as possible. As this can happen due to BGP's own mechanism of UPDATE messages, that produces a humongous amount of messages, BGP reduces the number of UPDATEs exchanged between two BGP routers by holding consecutive announcements from a router to a neighbor for a given amount of time. The BGP timer responsible for this task is called Minimum Route Advertisement Interval (MRAI), which has an important impact in routing convergence. The Software-Defined Networking (SDN) paradigm can be used to leverage interdomain routing services performance via the logically centralized controlling benefits of intradomain settings. SDN principles has been successfully deployed in data centers, LANs, and in several other studies, where each each AS is modeled with a logically centralized routing control, offering new opportunities and bringing BGP routing convergence improvements. In this work, an extensive survey is presented on the state-of-the-art about research efforts to achieve better BGP routing convergence time. Furthermore, I pinpoint the open issues in this research field and propose DeepBGP, to the best of my knowledge, the first hybrid framework endowed with a learning mechanism, that integrates the SDN paradigm within interdomain routing domains, to improve the interdomain routing convergence time. This is achieved by employing the LSTM learning technique that allows the tuning of MRAI value aiming to reduce the convergence time according to learned patterns from collected BGP UPDATE features. The PEERING platform was used to provide a real scenario that allows the sending of announcements to the Internet. With the benefits of having such an actual testbed I carried out experiments with protocol characteristics that can impact the routing convergence. The experimental results show that the adaptive MRAI in the DeepBGP framework is able to reduce the BGP routing convergence time when compared to the use of static MRAIs.Fundação de Amparo à Pesquisa do Estado do Amazonas (FAPEAM)Universidade Federal do AmazonasInstituto de ComputaçãoBrasilUFAMPrograma de Pós-graduação em InformáticaMota, Edjard Souzahttp://lattes.cnpq.br/0757666181169076Feitosa, Eduardo Luzeirohttp://lattes.cnpq.br/5939944067207881Santos, Eulanda Miranda doshttp://lattes.cnpq.br/3054990742969890Souza, Jose Neuman dehttp://lattes.cnpq.br/3614256141054800Silva, Ricardo Bennesby dahttp://lattes.cnpq.br/70781821545021632020-03-04T15:03:54Z2019-11-18info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisapplication/pdfSILVA, Ricardo Bennesby da. DeepBGP: a machine learning solution to reduce BGP routing convergence time by Fine-Tuning MRAI. 2019. 141 f. Tese (Doutorado em Informática) - Universidade Federal do Amazonas, Manaus, 2019.https://tede.ufam.edu.br/handle/tede/7697enginfo:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da UFAMinstname:Universidade Federal do Amazonas (UFAM)instacron:UFAM2020-03-05T05:03:59Zoai:https://tede.ufam.edu.br/handle/:tede/7697Biblioteca Digital de Teses e Dissertaçõeshttp://200.129.163.131:8080/PUBhttp://200.129.163.131:8080/oai/requestddbc@ufam.edu.br||ddbc@ufam.edu.bropendoar:65922020-03-05T05:03:59Biblioteca Digital de Teses e Dissertações da UFAM - Universidade Federal do Amazonas (UFAM)false |
dc.title.none.fl_str_mv |
DeepBGP: A Machine Learning Solution to reduce BGP Routing Convergence Time by Fine-Tuning MRAI A Machine-Learning Solution to reduce BGP Routing Convergence Time in a Hybrid SDN-Interdomain environment by Fine-Tuning MRAI |
title |
DeepBGP: A Machine Learning Solution to reduce BGP Routing Convergence Time by Fine-Tuning MRAI |
spellingShingle |
DeepBGP: A Machine Learning Solution to reduce BGP Routing Convergence Time by Fine-Tuning MRAI Silva, Ricardo Bennesby da Gerenciamento de redes Roteamento entre domínios Tempo de convergência Border Gateway Protocol Long Short-Term Memory Long Short-Term Memory CIÊNCIAS EXATAS E DA TERRA: CIÊNCIA DA COMPUTAÇÃO: SISTEMAS DE COMPUTAÇÃO bgp convergence time lstm network management interdomain routing |
title_short |
DeepBGP: A Machine Learning Solution to reduce BGP Routing Convergence Time by Fine-Tuning MRAI |
title_full |
DeepBGP: A Machine Learning Solution to reduce BGP Routing Convergence Time by Fine-Tuning MRAI |
title_fullStr |
DeepBGP: A Machine Learning Solution to reduce BGP Routing Convergence Time by Fine-Tuning MRAI |
title_full_unstemmed |
DeepBGP: A Machine Learning Solution to reduce BGP Routing Convergence Time by Fine-Tuning MRAI |
title_sort |
DeepBGP: A Machine Learning Solution to reduce BGP Routing Convergence Time by Fine-Tuning MRAI |
author |
Silva, Ricardo Bennesby da |
author_facet |
Silva, Ricardo Bennesby da http://lattes.cnpq.br/7078182154502163 |
author_role |
author |
author2 |
http://lattes.cnpq.br/7078182154502163 |
author2_role |
author |
dc.contributor.none.fl_str_mv |
Mota, Edjard Souza http://lattes.cnpq.br/0757666181169076 Feitosa, Eduardo Luzeiro http://lattes.cnpq.br/5939944067207881 Santos, Eulanda Miranda dos http://lattes.cnpq.br/3054990742969890 Souza, Jose Neuman de http://lattes.cnpq.br/3614256141054800 |
dc.contributor.author.fl_str_mv |
Silva, Ricardo Bennesby da http://lattes.cnpq.br/7078182154502163 |
dc.subject.por.fl_str_mv |
Gerenciamento de redes Roteamento entre domínios Tempo de convergência Border Gateway Protocol Long Short-Term Memory Long Short-Term Memory CIÊNCIAS EXATAS E DA TERRA: CIÊNCIA DA COMPUTAÇÃO: SISTEMAS DE COMPUTAÇÃO bgp convergence time lstm network management interdomain routing |
topic |
Gerenciamento de redes Roteamento entre domínios Tempo de convergência Border Gateway Protocol Long Short-Term Memory Long Short-Term Memory CIÊNCIAS EXATAS E DA TERRA: CIÊNCIA DA COMPUTAÇÃO: SISTEMAS DE COMPUTAÇÃO bgp convergence time lstm network management interdomain routing |
description |
The organization of the Internet is composed of administrative domains, known as Autonomous Systems (ASes), that exchange reachability information by means of the Border Gateway Protocol (BGP). Since a high convergence delay leads to packet losses and service unavailability, such a protocol has to converge as fast as possible. As this can happen due to BGP's own mechanism of UPDATE messages, that produces a humongous amount of messages, BGP reduces the number of UPDATEs exchanged between two BGP routers by holding consecutive announcements from a router to a neighbor for a given amount of time. The BGP timer responsible for this task is called Minimum Route Advertisement Interval (MRAI), which has an important impact in routing convergence. The Software-Defined Networking (SDN) paradigm can be used to leverage interdomain routing services performance via the logically centralized controlling benefits of intradomain settings. SDN principles has been successfully deployed in data centers, LANs, and in several other studies, where each each AS is modeled with a logically centralized routing control, offering new opportunities and bringing BGP routing convergence improvements. In this work, an extensive survey is presented on the state-of-the-art about research efforts to achieve better BGP routing convergence time. Furthermore, I pinpoint the open issues in this research field and propose DeepBGP, to the best of my knowledge, the first hybrid framework endowed with a learning mechanism, that integrates the SDN paradigm within interdomain routing domains, to improve the interdomain routing convergence time. This is achieved by employing the LSTM learning technique that allows the tuning of MRAI value aiming to reduce the convergence time according to learned patterns from collected BGP UPDATE features. The PEERING platform was used to provide a real scenario that allows the sending of announcements to the Internet. With the benefits of having such an actual testbed I carried out experiments with protocol characteristics that can impact the routing convergence. The experimental results show that the adaptive MRAI in the DeepBGP framework is able to reduce the BGP routing convergence time when compared to the use of static MRAIs. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-11-18 2020-03-04T15:03:54Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
SILVA, Ricardo Bennesby da. DeepBGP: a machine learning solution to reduce BGP routing convergence time by Fine-Tuning MRAI. 2019. 141 f. Tese (Doutorado em Informática) - Universidade Federal do Amazonas, Manaus, 2019. https://tede.ufam.edu.br/handle/tede/7697 |
identifier_str_mv |
SILVA, Ricardo Bennesby da. DeepBGP: a machine learning solution to reduce BGP routing convergence time by Fine-Tuning MRAI. 2019. 141 f. Tese (Doutorado em Informática) - Universidade Federal do Amazonas, Manaus, 2019. |
url |
https://tede.ufam.edu.br/handle/tede/7697 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal do Amazonas Instituto de Computação Brasil UFAM Programa de Pós-graduação em Informática |
publisher.none.fl_str_mv |
Universidade Federal do Amazonas Instituto de Computação Brasil UFAM Programa de Pós-graduação em Informática |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações da UFAM instname:Universidade Federal do Amazonas (UFAM) instacron:UFAM |
instname_str |
Universidade Federal do Amazonas (UFAM) |
instacron_str |
UFAM |
institution |
UFAM |
reponame_str |
Biblioteca Digital de Teses e Dissertações da UFAM |
collection |
Biblioteca Digital de Teses e Dissertações da UFAM |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações da UFAM - Universidade Federal do Amazonas (UFAM) |
repository.mail.fl_str_mv |
ddbc@ufam.edu.br||ddbc@ufam.edu.br |
_version_ |
1797040505045909504 |