Machine Learning Methods for Compensating Signal Distortions in Fiber-Optic Communication Lines

Standard

Machine Learning Methods for Compensating Signal Distortions in Fiber-Optic Communication Lines. / Sidelnikov, O. S.; Redyuk, A. A.; Fedoruk, M. P.

In: Optoelectronics, Instrumentation and Data Processing, Vol. 60, No. 1, 02.2024, p. 1-10.

Research output: Contribution to journal › Article › peer-review

BibTeX

@article{7ced12499b41445b80d14eb963b63702,

title = "Machine Learning Methods for Compensating Signal Distortions in Fiber-Optic Communication Lines",

abstract = "The article addresses current issues in the field of fiber-optic data transmission, related to the constant increase in demand for communication system bandwidth and nonlinear response. The main machine learning methods used to compensate for nonlinear signal distortions in long-haul coherent communication lines are presented, including neural networks of various architectures. The paper emphasizes the promise of machine learning-based solutions for enhancing the performance of optical fiber communication systems, thanks to their ability to derive effective and adaptive signal recovery schemes with low computational complexity.",

keywords = "digital signal processing, fiber optic communication systems, machine learning, neural networks, nonlinear distortion compensation, optical fiber nonlinearity",

author = "Sidelnikov, {O. S.} and Redyuk, {A. A.} and Fedoruk, {M. P.}",

note = "The work of O.S. Sidelnikov and A.A. Redyuk was supported by the Russian Science Foundation (project no. 17-72-30006). The work of M.P. Fedoruk was supported by the Russian Science Foundation (project no. 20-11-20040).",

year = "2024",

month = feb,

doi = "10.3103/S8756699024700018",

language = "English",

volume = "60",

pages = "1--10",

journal = "Optoelectronics, Instrumentation and Data Processing",

issn = "8756-6990",

publisher = "Allerton Press Inc.",

number = "1",

}

RIS

TY - JOUR

T1 - Machine Learning Methods for Compensating Signal Distortions in Fiber-Optic Communication Lines

AU - Sidelnikov, O. S.

AU - Redyuk, A. A.

AU - Fedoruk, M. P.

N1 - The work of O.S. Sidelnikov and A.A. Redyuk was supported by the Russian Science Foundation (project no. 17-72-30006). The work of M.P. Fedoruk was supported by the Russian Science Foundation (project no. 20-11-20040).

PY - 2024/2

Y1 - 2024/2

N2 - The article addresses current issues in the field of fiber-optic data transmission, related to the constant increase in demand for communication system bandwidth and nonlinear response. The main machine learning methods used to compensate for nonlinear signal distortions in long-haul coherent communication lines are presented, including neural networks of various architectures. The paper emphasizes the promise of machine learning-based solutions for enhancing the performance of optical fiber communication systems, thanks to their ability to derive effective and adaptive signal recovery schemes with low computational complexity.

AB - The article addresses current issues in the field of fiber-optic data transmission, related to the constant increase in demand for communication system bandwidth and nonlinear response. The main machine learning methods used to compensate for nonlinear signal distortions in long-haul coherent communication lines are presented, including neural networks of various architectures. The paper emphasizes the promise of machine learning-based solutions for enhancing the performance of optical fiber communication systems, thanks to their ability to derive effective and adaptive signal recovery schemes with low computational complexity.

KW - digital signal processing

KW - fiber optic communication systems

KW - machine learning

KW - neural networks

KW - nonlinear distortion compensation

KW - optical fiber nonlinearity

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85196484555&origin=inward&txGid=9653dfa0501ad8664dcf2e74dd950c05

UR - https://www.mendeley.com/catalogue/6708071c-9303-3318-8ccf-f2fd25bbeb06/

U2 - 10.3103/S8756699024700018

DO - 10.3103/S8756699024700018

M3 - Article

VL - 60

SP - 1

EP - 10

JO - Optoelectronics, Instrumentation and Data Processing

JF - Optoelectronics, Instrumentation and Data Processing

SN - 8756-6990

IS - 1

ER -

ID: 61161329