Short-Reach MCF-Based Systems Employing KK Receivers and Feedforward Neural Networks for ICXT Mitigation
This paper proposes and evaluates the use of machine learning (ML) techniques for mitigating the effect of the random inter-core crosstalk (ICXT) on 256 Gb/s short-reach systems employing weakly coupled multicore fiber (MCF) and Kramers–Kronig (KK) receivers. The performance improvement provided by...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Photonics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-6732/9/5/286 |
| _version_ | 1797496502959996928 |
|---|---|
| author | Derick Piedade Tiago Alves Tomás Brandão |
| author_facet | Derick Piedade Tiago Alves Tomás Brandão |
| author_sort | Derick Piedade |
| collection | DOAJ |
| description | This paper proposes and evaluates the use of machine learning (ML) techniques for mitigating the effect of the random inter-core crosstalk (ICXT) on 256 Gb/s short-reach systems employing weakly coupled multicore fiber (MCF) and Kramers–Kronig (KK) receivers. The performance improvement provided by the <i>k</i>-means clustering, <i>k</i> nearest neighbor (KNN) and feedforward neural network (FNN) techniques are assessed and compared with the system performance obtained without employing ML. The FNN proves to significantly improve the system performance by mitigating the impact of the ICXT on the received signal. This is achieved by employing only 10 neurons in the hidden layer and four input features for the training phase. It has been shown that <i>k</i>-means or KNN techniques do not provide performance improvement compared to the system without using ML. These conclusions are valid for direct detection MCF-based short-reach systems with the product between the skew (relative time delay between cores) and the symbol rate much lower than one (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>s</mi><mi>k</mi><mi>e</mi><mi>w</mi><mo>×</mo><mi>s</mi><mi>y</mi><mi>m</mi><mi>b</mi><mi>o</mi><mi>l</mi><mo> </mo><mi>r</mi><mi>a</mi><mi>t</mi><mi>e</mi><mo>≪</mo><mn>1</mn></mrow></semantics></math></inline-formula>). By employing the proposed FNN, the bit error rate (BER) always stood below <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>1.8</mn></mrow></msup></mrow></semantics></math></inline-formula> on all the time fractions under analysis (compared with 100 out of 626 occurrences above the BER threshold when ML was not used). For the BER threshold of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>1.8</mn></mrow></msup></mrow></semantics></math></inline-formula> and compared with the standard system operating without employing ML techniques, the system operating with the proposed FNN shows a received optical power improvement of almost 3 dB. |
| first_indexed | 2024-03-10T03:04:34Z |
| format | Article |
| id | doaj.art-4b405ecf0a2742d5a2777eca61464675 |
| institution | Directory Open Access Journal |
| issn | 2304-6732 |
| language | English |
| last_indexed | 2024-03-10T03:04:34Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Photonics |
| spelling | doaj.art-4b405ecf0a2742d5a2777eca614646752023-11-23T12:40:05ZengMDPI AGPhotonics2304-67322022-04-019528610.3390/photonics9050286Short-Reach MCF-Based Systems Employing KK Receivers and Feedforward Neural Networks for ICXT MitigationDerick Piedade0Tiago Alves1Tomás Brandão2Department of Information Science and Technologies, ISCTE-Instituto Universitário de Lisboa, 1649-026 Lisboa, PortugalDepartment of Information Science and Technologies, ISCTE-Instituto Universitário de Lisboa, 1649-026 Lisboa, PortugalDepartment of Information Science and Technologies, ISCTE-Instituto Universitário de Lisboa, 1649-026 Lisboa, PortugalThis paper proposes and evaluates the use of machine learning (ML) techniques for mitigating the effect of the random inter-core crosstalk (ICXT) on 256 Gb/s short-reach systems employing weakly coupled multicore fiber (MCF) and Kramers–Kronig (KK) receivers. The performance improvement provided by the <i>k</i>-means clustering, <i>k</i> nearest neighbor (KNN) and feedforward neural network (FNN) techniques are assessed and compared with the system performance obtained without employing ML. The FNN proves to significantly improve the system performance by mitigating the impact of the ICXT on the received signal. This is achieved by employing only 10 neurons in the hidden layer and four input features for the training phase. It has been shown that <i>k</i>-means or KNN techniques do not provide performance improvement compared to the system without using ML. These conclusions are valid for direct detection MCF-based short-reach systems with the product between the skew (relative time delay between cores) and the symbol rate much lower than one (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>s</mi><mi>k</mi><mi>e</mi><mi>w</mi><mo>×</mo><mi>s</mi><mi>y</mi><mi>m</mi><mi>b</mi><mi>o</mi><mi>l</mi><mo> </mo><mi>r</mi><mi>a</mi><mi>t</mi><mi>e</mi><mo>≪</mo><mn>1</mn></mrow></semantics></math></inline-formula>). By employing the proposed FNN, the bit error rate (BER) always stood below <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>1.8</mn></mrow></msup></mrow></semantics></math></inline-formula> on all the time fractions under analysis (compared with 100 out of 626 occurrences above the BER threshold when ML was not used). For the BER threshold of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mrow><mn>10</mn></mrow><mrow><mo>−</mo><mn>1.8</mn></mrow></msup></mrow></semantics></math></inline-formula> and compared with the standard system operating without employing ML techniques, the system operating with the proposed FNN shows a received optical power improvement of almost 3 dB.https://www.mdpi.com/2304-6732/9/5/286short-reach systemsmulticore fibermachine learningKramers–Kronig receiver |
| spellingShingle | Derick Piedade Tiago Alves Tomás Brandão Short-Reach MCF-Based Systems Employing KK Receivers and Feedforward Neural Networks for ICXT Mitigation Photonics short-reach systems multicore fiber machine learning Kramers–Kronig receiver |
| title | Short-Reach MCF-Based Systems Employing KK Receivers and Feedforward Neural Networks for ICXT Mitigation |
| title_full | Short-Reach MCF-Based Systems Employing KK Receivers and Feedforward Neural Networks for ICXT Mitigation |
| title_fullStr | Short-Reach MCF-Based Systems Employing KK Receivers and Feedforward Neural Networks for ICXT Mitigation |
| title_full_unstemmed | Short-Reach MCF-Based Systems Employing KK Receivers and Feedforward Neural Networks for ICXT Mitigation |
| title_short | Short-Reach MCF-Based Systems Employing KK Receivers and Feedforward Neural Networks for ICXT Mitigation |
| title_sort | short reach mcf based systems employing kk receivers and feedforward neural networks for icxt mitigation |
| topic | short-reach systems multicore fiber machine learning Kramers–Kronig receiver |
| url | https://www.mdpi.com/2304-6732/9/5/286 |
| work_keys_str_mv | AT derickpiedade shortreachmcfbasedsystemsemployingkkreceiversandfeedforwardneuralnetworksforicxtmitigation AT tiagoalves shortreachmcfbasedsystemsemployingkkreceiversandfeedforwardneuralnetworksforicxtmitigation AT tomasbrandao shortreachmcfbasedsystemsemployingkkreceiversandfeedforwardneuralnetworksforicxtmitigation |