An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2012 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://www.sciencedirect.com/science/article/pii/S1877050912005133 http://hdl.handle.net/11449/122477 |
Resumo: | Connectivity is the basic factor for the proper operation of any wireless network. In a mobile wireless sensor network it is a challenge for applications and protocols to deal with connectivity problems, as links might get up and down frequently. In these scenarios, having knowledge of the node remaining connectivity time could both improve the performance of the protocols (e.g. handoff mechanisms) and save possible scarce nodes resources (CPU, bandwidth, and energy) by preventing unfruitful transmissions. The current paper provides a solution called Genetic Machine Learning Algorithm (GMLA) to forecast the remainder connectivity time in mobile environments. It consists in combining Classifier Systems with a Markov chain model of the RF link quality. The main advantage of using an evolutionary approach is that the Markov model parameters can be discovered on-the-fly, making it possible to cope with unknown environments and mobility patterns. Simulation results show that the proposal is a very suitable solution, as it overcomes the performance obtained by similar approaches. |
id |
UNSP_2fa9425b111be263243606ed19c34ac2 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/122477 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
An evolutionary approach to improve connectivity prediction in mobile wireless sensor networksWireless sensor networksMobilityConnectivity predictionGenetic algorithmClassifier SystemsConnectivity is the basic factor for the proper operation of any wireless network. In a mobile wireless sensor network it is a challenge for applications and protocols to deal with connectivity problems, as links might get up and down frequently. In these scenarios, having knowledge of the node remaining connectivity time could both improve the performance of the protocols (e.g. handoff mechanisms) and save possible scarce nodes resources (CPU, bandwidth, and energy) by preventing unfruitful transmissions. The current paper provides a solution called Genetic Machine Learning Algorithm (GMLA) to forecast the remainder connectivity time in mobile environments. It consists in combining Classifier Systems with a Markov chain model of the RF link quality. The main advantage of using an evolutionary approach is that the Markov model parameters can be discovered on-the-fly, making it possible to cope with unknown environments and mobility patterns. Simulation results show that the proposal is a very suitable solution, as it overcomes the performance obtained by similar approaches.Universidade Estadual Paulista Júlio de Mesquita Filho, Departamento de Ciência da Computação e Estatística, Instituto de Biociências Letras e Ciências Exatas de São José do Rio PretoUniversidade Federal de Santa Catarina (UFSC)Universidade Estadual Paulista (Unesp)Otto-Von-Guericke-Univesitat MagdeburgAraújo, Gustavo Medeiros dePinto, Alex Sandro Roschildt [UNESP]Kaiser, JörgBecker, Leandro Buss2015-04-27T11:55:47Z2015-04-27T11:55:47Z2012info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article1100-1105application/pdfhttp://www.sciencedirect.com/science/article/pii/S1877050912005133Procedia Computer Science, v. 10, p. 1100-1105, 2012.1877-0509http://hdl.handle.net/11449/12247710.1016/j.procs.2012.06.156ISSN1877-0509-2012-10-1100-1105.pdf0555619693238543Currículo Lattesreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProcedia Computer Science0,258info:eu-repo/semantics/openAccess2024-01-07T06:24:10Zoai:repositorio.unesp.br:11449/122477Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T22:20:23.756467Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks |
title |
An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks |
spellingShingle |
An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks Araújo, Gustavo Medeiros de Wireless sensor networks Mobility Connectivity prediction Genetic algorithm Classifier Systems |
title_short |
An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks |
title_full |
An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks |
title_fullStr |
An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks |
title_full_unstemmed |
An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks |
title_sort |
An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks |
author |
Araújo, Gustavo Medeiros de |
author_facet |
Araújo, Gustavo Medeiros de Pinto, Alex Sandro Roschildt [UNESP] Kaiser, Jörg Becker, Leandro Buss |
author_role |
author |
author2 |
Pinto, Alex Sandro Roschildt [UNESP] Kaiser, Jörg Becker, Leandro Buss |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de Santa Catarina (UFSC) Universidade Estadual Paulista (Unesp) Otto-Von-Guericke-Univesitat Magdeburg |
dc.contributor.author.fl_str_mv |
Araújo, Gustavo Medeiros de Pinto, Alex Sandro Roschildt [UNESP] Kaiser, Jörg Becker, Leandro Buss |
dc.subject.por.fl_str_mv |
Wireless sensor networks Mobility Connectivity prediction Genetic algorithm Classifier Systems |
topic |
Wireless sensor networks Mobility Connectivity prediction Genetic algorithm Classifier Systems |
description |
Connectivity is the basic factor for the proper operation of any wireless network. In a mobile wireless sensor network it is a challenge for applications and protocols to deal with connectivity problems, as links might get up and down frequently. In these scenarios, having knowledge of the node remaining connectivity time could both improve the performance of the protocols (e.g. handoff mechanisms) and save possible scarce nodes resources (CPU, bandwidth, and energy) by preventing unfruitful transmissions. The current paper provides a solution called Genetic Machine Learning Algorithm (GMLA) to forecast the remainder connectivity time in mobile environments. It consists in combining Classifier Systems with a Markov chain model of the RF link quality. The main advantage of using an evolutionary approach is that the Markov model parameters can be discovered on-the-fly, making it possible to cope with unknown environments and mobility patterns. Simulation results show that the proposal is a very suitable solution, as it overcomes the performance obtained by similar approaches. |
publishDate |
2012 |
dc.date.none.fl_str_mv |
2012 2015-04-27T11:55:47Z 2015-04-27T11:55:47Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://www.sciencedirect.com/science/article/pii/S1877050912005133 Procedia Computer Science, v. 10, p. 1100-1105, 2012. 1877-0509 http://hdl.handle.net/11449/122477 10.1016/j.procs.2012.06.156 ISSN1877-0509-2012-10-1100-1105.pdf 0555619693238543 |
url |
http://www.sciencedirect.com/science/article/pii/S1877050912005133 http://hdl.handle.net/11449/122477 |
identifier_str_mv |
Procedia Computer Science, v. 10, p. 1100-1105, 2012. 1877-0509 10.1016/j.procs.2012.06.156 ISSN1877-0509-2012-10-1100-1105.pdf 0555619693238543 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Procedia Computer Science 0,258 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
1100-1105 application/pdf |
dc.source.none.fl_str_mv |
Currículo Lattes reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808129417033023488 |