Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Tese |
Idioma: | por |
Título da fonte: | Biblioteca Digital de Teses e Dissertações da INATEL |
Texto Completo: | https://tede.inatel.br:8080/tede/handle/tede/250 |
Resumo: | The thesis main goals are proposing and evaluating machine learning (ML)-based linearization schemes for analog radio over fiber (A-RoF) systems from the fifth and sixth generations of mobile communications (5G and 6G). The performance analyses of the linearization techniques were based on the use of polynomial models to represent the non-linearities of the A-RoF system and artificial neural networks (ANNs) to perform pre-and/or post-distortion of the transmitted signal. The main A-RoF system non-linear components were taken into account. First, a linearization scheme was developed for the Mach-Zehnder modulator (MZM). It employs a multi-layer perceptron (MLP) ANN to perform the pre-and/or post-distortion of the transmitted signal. The electrical power amplifier (PA) non-linear effects were also evaluated. PA is commonly used in A-RoF systems to amplify the radio frequency (RF) signal before being radiated. In this case, it is required a recurrent neural network (RNN), which is able to deal with the power amplifier memory effect. RNN has an internal memory structure that can be properly designed to compensate for the non-linear degradation, considering the memoryless non-linear distortions introduced by the MZM and the memory non-linear distortion introduced by the PA. Finally, the chromatic dispersion (CD) introduced by the optical fiber was also taken into account, since the transport optical link needs to be extended to provide coverage in remote areas. The augmented real-valued time delay neural network (ARVTDNN) was used, since it allows simultaneously compensating all the aforementioned effects. All results were obtained by using Python simulations. This work also presents the application of ARVTDNN linearization scheme into a fiber/wireless (FiWi) system. Basically, the obtained results from this thesis demonstrate that ML-based linearization schemes represent potential solutions to maximize the performance of A-RoF systems from the 5G and 6G transport networks. |
id |
INAT_e28b3ce0a599cff7c0edae05d8f91190 |
---|---|
oai_identifier_str |
oai:localhost:tede/250 |
network_acronym_str |
INAT |
network_name_str |
Biblioteca Digital de Teses e Dissertações da INATEL |
repository_id_str |
|
spelling |
J??nior, Arismar Cerqueira1703406475581759http://lattes.cnpq.br/1703406475581759Mendes , Luciano Leonel9119890339398363http://lattes.cnpq.br/9119890339398363J??nior , Arismar Cerqueira945.507.195-91http://lattes.cnpq.br/1703406475581759Segatto, Marcelo Eduardo2379169013108798http://lattes.cnpq.br/2379169013108798Figueiredo, Felipe Augusto0188611850092267http://lattes.cnpq.br/0188611850092267Ribeiro , Jose Ant??nio9987344139958522http://lattes.cnpq.br/99873441399585225254089220289963http://lattes.cnpq.br/5254089220289963Pereira, Luiz Augusto2024-03-21T17:46:25Z2023-07-06Pereira, Luiz Augusto. Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization. 2023. [148 p.]. Tese( Mestrado em Engenharia de Telecomunica????es) - Instituto Nacional de Telecomunica????es, [Santa Rita do Sapuca??] .https://tede.inatel.br:8080/tede/handle/tede/250The thesis main goals are proposing and evaluating machine learning (ML)-based linearization schemes for analog radio over fiber (A-RoF) systems from the fifth and sixth generations of mobile communications (5G and 6G). The performance analyses of the linearization techniques were based on the use of polynomial models to represent the non-linearities of the A-RoF system and artificial neural networks (ANNs) to perform pre-and/or post-distortion of the transmitted signal. The main A-RoF system non-linear components were taken into account. First, a linearization scheme was developed for the Mach-Zehnder modulator (MZM). It employs a multi-layer perceptron (MLP) ANN to perform the pre-and/or post-distortion of the transmitted signal. The electrical power amplifier (PA) non-linear effects were also evaluated. PA is commonly used in A-RoF systems to amplify the radio frequency (RF) signal before being radiated. In this case, it is required a recurrent neural network (RNN), which is able to deal with the power amplifier memory effect. RNN has an internal memory structure that can be properly designed to compensate for the non-linear degradation, considering the memoryless non-linear distortions introduced by the MZM and the memory non-linear distortion introduced by the PA. Finally, the chromatic dispersion (CD) introduced by the optical fiber was also taken into account, since the transport optical link needs to be extended to provide coverage in remote areas. The augmented real-valued time delay neural network (ARVTDNN) was used, since it allows simultaneously compensating all the aforementioned effects. All results were obtained by using Python simulations. This work also presents the application of ARVTDNN linearization scheme into a fiber/wireless (FiWi) system. Basically, the obtained results from this thesis demonstrate that ML-based linearization schemes represent potential solutions to maximize the performance of A-RoF systems from the 5G and 6G transport networks.O objetivo deste trabalho e propor e avaliar o desempenho de esquemas de lineariza????o baseados em aprendizado de m??quina (ML - machine learning), aplicados a sistemas anal??gicos r??dio sobre fibra (A-RoF - analog radio over fiber) para o transporte de sinais da quinta gera????o de comunica????es m??veis (5G - fifth generation of mobile communications) e das futuras redes de comunica????es m??veis de sexta gera????o (6G - sixth generation of mobile communications). As an??lises de desempenho das t??cnicas de lineariza????o baseiam-se na utiliza????o de modelos polinomiais para modelar as n??o-linearidades do sistema A-RoF e utilizar redes neurais para realizar a pre-e/ou pos-distor????o do sinal transmitido. Considerou-se os principais componentes do sistemas A-RoF que apresentam comportamento nao-linear. Inicialmente, prop??e-se um esquema de lineariza????o para o modulador eletro-??ptico de Mach-Zehnder (MZM - Mach-Zehnder modulator). Nesta abordagem, emprega-se uma rede neural perceptron com multiplas camadas (MLP - multi-layer perceptron) para realizar a pr??- e/ou p??s-distor????o do sinal transmitido. Avalia-se tamb??m os efeitos n??o-lineares do amplificador de pot??ncia el??trico (PA - power amplifier), comumente utilizado em sistemas A-RoF para amplificar o sinal de radio-frequencia (RF - radio frequency) antes da radia????o. Neste caso, utiliza-se a rede neural recorrente (RNN - recurrent neural network), que e capaz de lidar com o efeito mem??ria do amplificador. A RNN possui uma estrutura de mem??ria interna, que pode ser devidamente dimensionada para compensar as degrada????es n??o-lineares sem mem??ria do MZM e com mem??ria do PA. Finalmente, a dispers??o crom??tica da fibra ??ptica tamb??m foi considerada, uma vez que o enlace ??ptico de transporte precisa ser estendido visando fornecer cobertura em ??reas remotas. Para tal, utiliza-se a rede neural de atraso de tempo real aumentada (ARVTDNN - augmented real-valued time delay neural network), pois esta arquitetura permite compensar os efeitos acima mencionados. Todos os resultados destas an??lises foram obtidos usando simula????es em Python. Este trabalho tamb??m apresenta a aplica????o da t??cnica ARVTDNN em um sistema fibra/r??dio (FiWi - fiber/wireless). Em linhas gerais, os resultados obtidos nessa tese demonstram que o uso de esquemas de lineariza????o baseados em ML s??o potenciais para maximizar o desempenho de sistemas A-RoF em redes de transporte 5G e 6G.Submitted by Tede Dspace (tede@inatel.br) on 2024-03-21T17:45:53Z No. of bitstreams: 1 Luiz Augusto Melo Pereira (1).pdf: 15899129 bytes, checksum: 5c67896850b4b5633980d73796392edd (MD5)Made available in DSpace on 2024-03-21T17:46:25Z (GMT). No. of bitstreams: 1 Luiz Augusto Melo Pereira (1).pdf: 15899129 bytes, checksum: 5c67896850b4b5633980d73796392edd (MD5) Previous issue date: 2023-07-06application/pdfhttp://tede.inatel.br:8080/jspui/retrieve/1984/Luiz%20Augusto%20Melo%20Pereira%20%281%29.pdf.jpgporInstituto Nacional de Telecomunica????esMestrado em Engenharia de Telecomunica????esINATELBrasilInstituto Nacional de Telecomunica????es5G; 6G; aprendizado de m??quina; p??s-distor????o; pr??-distor????o; redes neurais artificiais e r??dio sobre fibra anal??gico;55G; 6G; analog radio over fiber; ANN; machine learning, post-distortion and pre-distortion;Engenharia - Telecomunica????esMachine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearizationinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisinfo:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da INATELinstname:Instituto Nacional de Telecomunicações (INATEL)instacron:INATELLICENSElicense.txtlicense.txttext/plain; charset=utf-850http://localhost:8080/tede/bitstream/tede/250/1/license.txtad97de64637545abb37de9243411913cMD51ORIGINALLuiz Augusto Melo Pereira (1).pdfLuiz Augusto Melo Pereira (1).pdfapplication/pdf15899129http://localhost:8080/tede/bitstream/tede/250/2/Luiz+Augusto+Melo+Pereira+%281%29.pdf5c67896850b4b5633980d73796392eddMD52TEXTLuiz Augusto Melo Pereira (1).pdf.txtLuiz Augusto Melo Pereira (1).pdf.txttext/plain426108http://localhost:8080/tede/bitstream/tede/250/3/Luiz+Augusto+Melo+Pereira+%281%29.pdf.txtfa85de83e5358ef3a4f9f6bee096bbccMD53THUMBNAILLuiz Augusto Melo Pereira (1).pdf.jpgLuiz Augusto Melo Pereira (1).pdf.jpgimage/jpeg3759http://localhost:8080/tede/bitstream/tede/250/4/Luiz+Augusto+Melo+Pereira+%281%29.pdf.jpg67260591f7fa538f04730f96459cae04MD54tede/2502024-03-22 01:00:14.355oai:localhost:tede/250aHR0cDovL2NyZWF0aXZlY29tbW9ucy5vcmcvbGljZW5zZXMvYnktbmMtbmQvNC4wLy4=Biblioteca Digital de Teses e Dissertaçõeshttp://tede.inatel.br:8080/jspui/PUBhttp://tede.inatel.br:8080/oai/requestbiblioteca@inatel.br || biblioteca.atendimento@inatel.bropendoar:2024-03-22T04:00:14Biblioteca Digital de Teses e Dissertações da INATEL - Instituto Nacional de Telecomunicações (INATEL)false |
dc.title.por.fl_str_mv |
Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization |
title |
Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization |
spellingShingle |
Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization Pereira, Luiz Augusto 5G; 6G; aprendizado de m??quina; p??s-distor????o; pr??-distor????o; redes neurais artificiais e r??dio sobre fibra anal??gico; 55G; 6G; analog radio over fiber; ANN; machine learning, post-distortion and pre-distortion; Engenharia - Telecomunica????es |
title_short |
Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization |
title_full |
Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization |
title_fullStr |
Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization |
title_full_unstemmed |
Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization |
title_sort |
Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization |
author |
Pereira, Luiz Augusto |
author_facet |
Pereira, Luiz Augusto |
author_role |
author |
dc.contributor.advisor2ID.por.fl_str_mv |
9119890339398363 |
dc.contributor.advisor1.fl_str_mv |
J??nior, Arismar Cerqueira |
dc.contributor.advisor1ID.fl_str_mv |
1703406475581759 |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/1703406475581759 |
dc.contributor.advisor2.fl_str_mv |
Mendes , Luciano Leonel |
dc.contributor.advisor2Lattes.fl_str_mv |
http://lattes.cnpq.br/9119890339398363 |
dc.contributor.referee1.fl_str_mv |
J??nior , Arismar Cerqueira |
dc.contributor.referee1ID.fl_str_mv |
945.507.195-91 |
dc.contributor.referee1Lattes.fl_str_mv |
http://lattes.cnpq.br/1703406475581759 |
dc.contributor.referee2.fl_str_mv |
Segatto, Marcelo Eduardo |
dc.contributor.referee2ID.fl_str_mv |
2379169013108798 |
dc.contributor.referee2Lattes.fl_str_mv |
http://lattes.cnpq.br/2379169013108798 |
dc.contributor.referee3.fl_str_mv |
Figueiredo, Felipe Augusto |
dc.contributor.referee3ID.fl_str_mv |
0188611850092267 |
dc.contributor.referee3Lattes.fl_str_mv |
http://lattes.cnpq.br/0188611850092267 |
dc.contributor.referee4.fl_str_mv |
Ribeiro , Jose Ant??nio |
dc.contributor.referee4ID.fl_str_mv |
9987344139958522 |
dc.contributor.referee4Lattes.fl_str_mv |
http://lattes.cnpq.br/9987344139958522 |
dc.contributor.authorID.fl_str_mv |
5254089220289963 |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/5254089220289963 |
dc.contributor.author.fl_str_mv |
Pereira, Luiz Augusto |
contributor_str_mv |
J??nior, Arismar Cerqueira Mendes , Luciano Leonel J??nior , Arismar Cerqueira Segatto, Marcelo Eduardo Figueiredo, Felipe Augusto Ribeiro , Jose Ant??nio |
dc.subject.por.fl_str_mv |
5G; 6G; aprendizado de m??quina; p??s-distor????o; pr??-distor????o; redes neurais artificiais e r??dio sobre fibra anal??gico; |
topic |
5G; 6G; aprendizado de m??quina; p??s-distor????o; pr??-distor????o; redes neurais artificiais e r??dio sobre fibra anal??gico; 55G; 6G; analog radio over fiber; ANN; machine learning, post-distortion and pre-distortion; Engenharia - Telecomunica????es |
dc.subject.eng.fl_str_mv |
55G; 6G; analog radio over fiber; ANN; machine learning, post-distortion and pre-distortion; |
dc.subject.cnpq.fl_str_mv |
Engenharia - Telecomunica????es |
description |
The thesis main goals are proposing and evaluating machine learning (ML)-based linearization schemes for analog radio over fiber (A-RoF) systems from the fifth and sixth generations of mobile communications (5G and 6G). The performance analyses of the linearization techniques were based on the use of polynomial models to represent the non-linearities of the A-RoF system and artificial neural networks (ANNs) to perform pre-and/or post-distortion of the transmitted signal. The main A-RoF system non-linear components were taken into account. First, a linearization scheme was developed for the Mach-Zehnder modulator (MZM). It employs a multi-layer perceptron (MLP) ANN to perform the pre-and/or post-distortion of the transmitted signal. The electrical power amplifier (PA) non-linear effects were also evaluated. PA is commonly used in A-RoF systems to amplify the radio frequency (RF) signal before being radiated. In this case, it is required a recurrent neural network (RNN), which is able to deal with the power amplifier memory effect. RNN has an internal memory structure that can be properly designed to compensate for the non-linear degradation, considering the memoryless non-linear distortions introduced by the MZM and the memory non-linear distortion introduced by the PA. Finally, the chromatic dispersion (CD) introduced by the optical fiber was also taken into account, since the transport optical link needs to be extended to provide coverage in remote areas. The augmented real-valued time delay neural network (ARVTDNN) was used, since it allows simultaneously compensating all the aforementioned effects. All results were obtained by using Python simulations. This work also presents the application of ARVTDNN linearization scheme into a fiber/wireless (FiWi) system. Basically, the obtained results from this thesis demonstrate that ML-based linearization schemes represent potential solutions to maximize the performance of A-RoF systems from the 5G and 6G transport networks. |
publishDate |
2023 |
dc.date.issued.fl_str_mv |
2023-07-06 |
dc.date.accessioned.fl_str_mv |
2024-03-21T17:46:25Z |
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.citation.fl_str_mv |
Pereira, Luiz Augusto. Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization. 2023. [148 p.]. Tese( Mestrado em Engenharia de Telecomunica????es) - Instituto Nacional de Telecomunica????es, [Santa Rita do Sapuca??] . |
dc.identifier.uri.fl_str_mv |
https://tede.inatel.br:8080/tede/handle/tede/250 |
identifier_str_mv |
Pereira, Luiz Augusto. Machine Learning Applied to 5G and Towards 6G Fiber/Wireless Systems Linearization. 2023. [148 p.]. Tese( Mestrado em Engenharia de Telecomunica????es) - Instituto Nacional de Telecomunica????es, [Santa Rita do Sapuca??] . |
url |
https://tede.inatel.br:8080/tede/handle/tede/250 |
dc.language.iso.fl_str_mv |
por |
language |
por |
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 |
Instituto Nacional de Telecomunica????es |
dc.publisher.program.fl_str_mv |
Mestrado em Engenharia de Telecomunica????es |
dc.publisher.initials.fl_str_mv |
INATEL |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Instituto Nacional de Telecomunica????es |
publisher.none.fl_str_mv |
Instituto Nacional de Telecomunica????es |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações da INATEL instname:Instituto Nacional de Telecomunicações (INATEL) instacron:INATEL |
instname_str |
Instituto Nacional de Telecomunicações (INATEL) |
instacron_str |
INATEL |
institution |
INATEL |
reponame_str |
Biblioteca Digital de Teses e Dissertações da INATEL |
collection |
Biblioteca Digital de Teses e Dissertações da INATEL |
bitstream.url.fl_str_mv |
http://localhost:8080/tede/bitstream/tede/250/1/license.txt http://localhost:8080/tede/bitstream/tede/250/2/Luiz+Augusto+Melo+Pereira+%281%29.pdf http://localhost:8080/tede/bitstream/tede/250/3/Luiz+Augusto+Melo+Pereira+%281%29.pdf.txt http://localhost:8080/tede/bitstream/tede/250/4/Luiz+Augusto+Melo+Pereira+%281%29.pdf.jpg |
bitstream.checksum.fl_str_mv |
ad97de64637545abb37de9243411913c 5c67896850b4b5633980d73796392edd fa85de83e5358ef3a4f9f6bee096bbcc 67260591f7fa538f04730f96459cae04 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações da INATEL - Instituto Nacional de Telecomunicações (INATEL) |
repository.mail.fl_str_mv |
biblioteca@inatel.br || biblioteca.atendimento@inatel.br |
_version_ |
1800214191908323328 |