Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems

Detalhes bibliográficos
Ano de defesa: 2024
Autor(a) principal: Dantas, Lucas Cardinal [UNESP]
Orientador(a): Não Informado pela instituição
Banca de defesa: Não Informado pela instituição
Tipo de documento: Dissertação
Tipo de acesso: Acesso aberto
Idioma: eng
Instituição de defesa: Universidade Estadual Paulista (Unesp)
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://hdl.handle.net/11449/259327
Resumo: In this work, we propose using neural networks to mitigate intersymbol interference introduced by the fiber in optical communication systems. This mitigation method is well known, nevertheless the majority of studies that we traced back in the literature process only the symbol of interest, and consequently, cannot compensate the intersymbol interference. The approach presented in this work includes also using adjacent symbols, as there is a correlation between these symbols distortion. But, this increases the computational complexity. For that reason, we also analyzed the computational complexity to train the neural network. We were not able to trace back in the literature works that performed this multi-objective analysis, taking into account the adjacent symbols for training the neural network and also the computational complexity.
id UNSP_cbd9036a317019b9ae9d770dab20a73f
oai_identifier_str oai:repositorio.unesp.br:11449/259327
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str
spelling Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systemsOtimização multi-objetiva de um equalizador não linear baseado em redes neurais artificiais em sistemas coerentes digitais sem repetidoresComunicações óticasInteligência artificialKerr, Efeito deIn this work, we propose using neural networks to mitigate intersymbol interference introduced by the fiber in optical communication systems. This mitigation method is well known, nevertheless the majority of studies that we traced back in the literature process only the symbol of interest, and consequently, cannot compensate the intersymbol interference. The approach presented in this work includes also using adjacent symbols, as there is a correlation between these symbols distortion. But, this increases the computational complexity. For that reason, we also analyzed the computational complexity to train the neural network. We were not able to trace back in the literature works that performed this multi-objective analysis, taking into account the adjacent symbols for training the neural network and also the computational complexity.Neste projeto, propomos a utilização de redes neurais para mitigação da interferência intersimbólica introduzida pela fibra em sistemas de comunicações ópticas coerentes digitais. Este método de mitigação é conhecido, no entanto a maioria dos estudos encontrados na literatura processam apenas o símbolo de interesse e consequentemente não conseguem compensar a interferência intersimbólica. A proposta apresentada neste trabalho envolve utilizar também os símbolos adjacentes, uma vez que existe correlação entre a distorção destes símbolos. No entanto isto aumenta a complexidade computacional. Por esta razão, analisamos também a complexidade computacional para efetuar o treinamento da rede. Não encontramos anteriormente na literatura trabalhos que efetuaram esta análise multi-objetiva, levando em conta os símbolos adjacentes no treinamento da rede neural e também a complexidade computacional.Universidade Estadual Paulista (Unesp)Garde, Ivan Aritz Aldaya [UNESP]Universidade Estadual Paulista (Unesp)Guillardi Júnior, Hildo [UNESP]Dantas, Lucas Cardinal [UNESP]2024-12-19T19:22:09Z2024-12-19T19:22:09Z2024-11-28info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfDANTAS, L. C. Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems. 2024. Dissertação (Mestrado em Engenharia Elétrica) — Faculdade de Engenharia, Universidade Estadual Paulista "Júlio de Mesquita Filho", São João da Boa Vista, 2024.https://hdl.handle.net/11449/25932733004170002P24821501054965664enginfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESP2026-01-17T05:02:10Zoai:repositorio.unesp.br:11449/259327Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestrepositoriounesp@unesp.bropendoar:29462026-01-17T05:02:10Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems
Otimização multi-objetiva de um equalizador não linear baseado em redes neurais artificiais em sistemas coerentes digitais sem repetidores
title Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems
spellingShingle Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems
Dantas, Lucas Cardinal [UNESP]
Comunicações óticas
Inteligência artificial
Kerr, Efeito de
title_short Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems
title_full Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems
title_fullStr Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems
title_full_unstemmed Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems
title_sort Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems
author Dantas, Lucas Cardinal [UNESP]
author_facet Dantas, Lucas Cardinal [UNESP]
author_role author
dc.contributor.none.fl_str_mv Garde, Ivan Aritz Aldaya [UNESP]
Universidade Estadual Paulista (Unesp)
Guillardi Júnior, Hildo [UNESP]
dc.contributor.author.fl_str_mv Dantas, Lucas Cardinal [UNESP]
dc.subject.por.fl_str_mv Comunicações óticas
Inteligência artificial
Kerr, Efeito de
topic Comunicações óticas
Inteligência artificial
Kerr, Efeito de
description In this work, we propose using neural networks to mitigate intersymbol interference introduced by the fiber in optical communication systems. This mitigation method is well known, nevertheless the majority of studies that we traced back in the literature process only the symbol of interest, and consequently, cannot compensate the intersymbol interference. The approach presented in this work includes also using adjacent symbols, as there is a correlation between these symbols distortion. But, this increases the computational complexity. For that reason, we also analyzed the computational complexity to train the neural network. We were not able to trace back in the literature works that performed this multi-objective analysis, taking into account the adjacent symbols for training the neural network and also the computational complexity.
publishDate 2024
dc.date.none.fl_str_mv 2024-12-19T19:22:09Z
2024-12-19T19:22:09Z
2024-11-28
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv DANTAS, L. C. Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems. 2024. Dissertação (Mestrado em Engenharia Elétrica) — Faculdade de Engenharia, Universidade Estadual Paulista "Júlio de Mesquita Filho", São João da Boa Vista, 2024.
https://hdl.handle.net/11449/259327
33004170002P2
4821501054965664
identifier_str_mv DANTAS, L. C. Multi-objective optimization of a neural network-based nonlinear equalizer in unrepeated digital coherent optical communication systems. 2024. Dissertação (Mestrado em Engenharia Elétrica) — Faculdade de Engenharia, Universidade Estadual Paulista "Júlio de Mesquita Filho", São João da Boa Vista, 2024.
33004170002P2
4821501054965664
url https://hdl.handle.net/11449/259327
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 Estadual Paulista (Unesp)
publisher.none.fl_str_mv Universidade Estadual Paulista (Unesp)
dc.source.none.fl_str_mv 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 repositoriounesp@unesp.br
_version_ 1854954870090498048