Complex-Valued CNN Nonlinear Equalization Enabled 36-Tbit/s (45×800-Gbit/s) WDM Transmission Over 3150 Km Using Silicon-Based IC-TROSA
The growing Internet traffic urgently needs large-capacity and cost-effective optical transmissions. To maintain system performance under low-cost conditions, the silicon-based integrated coherent transmit and receive optical sub-assembly (IC-TROSA) and the complex-valued convolutional neural networ...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Photonics Journal |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10777400/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533420009684992 |
|---|---|
| author | Yuhan Gong Xiaoshuo Jia Ying Zhu Kailai Liu Ming Luo Jin Tao Zhixue He Chao Li Zichen Liu Yan Li Jian Wu Chao Yang |
| author_facet | Yuhan Gong Xiaoshuo Jia Ying Zhu Kailai Liu Ming Luo Jin Tao Zhixue He Chao Li Zichen Liu Yan Li Jian Wu Chao Yang |
| author_sort | Yuhan Gong |
| collection | DOAJ |
| description | The growing Internet traffic urgently needs large-capacity and cost-effective optical transmissions. To maintain system performance under low-cost conditions, the silicon-based integrated coherent transmit and receive optical sub-assembly (IC-TROSA) and the complex-valued convolutional neural network (CVCNN) algorithm provide an effective solution for high-capacity and long-distance WDM optical transmission. The proposed CVCNN can improve the system performance under nonlinear damage conditions, which fully considers the orthogonality of IQ signals in this paper. This algorithm exhibits different equalization performances for 64QAM signals under various encoding schemes considering 20%-overhead, achieving up to 2dB maximum decrease in the required optical signal-to-noise ratio at the optical back-to-back case. Regarding transmission distance, employing CVCNN extends the maximum reach from 3500 km to 3850 km. The paper also demonstrates the application of CVCNN in WDM systems, enhancing system performance across different WDM encoding schemes. Finally, the experiment verified that CVCNN requires fewer computational resources than real-valued convolutional neural networks (RVCNN). |
| format | Article |
| id | doaj-art-84cbfc4e2a694cb6b5a412d17786dd86 |
| institution | Kabale University |
| issn | 1943-0655 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Photonics Journal |
| spelling | doaj-art-84cbfc4e2a694cb6b5a412d17786dd862025-01-16T00:00:12ZengIEEEIEEE Photonics Journal1943-06552025-01-011711810.1109/JPHOT.2024.351079110777400Complex-Valued CNN Nonlinear Equalization Enabled 36-Tbit/s (45×800-Gbit/s) WDM Transmission Over 3150 Km Using Silicon-Based IC-TROSAYuhan Gong0Xiaoshuo Jia1https://orcid.org/0009-0003-2786-2911Ying Zhu2https://orcid.org/0000-0001-9250-3550Kailai Liu3Ming Luo4https://orcid.org/0000-0002-7291-1706Jin Tao5https://orcid.org/0000-0003-2212-3880Zhixue He6https://orcid.org/0000-0001-8533-2247Chao Li7https://orcid.org/0000-0001-6623-131XZichen Liu8Yan Li9https://orcid.org/0000-0003-1527-3418Jian Wu10https://orcid.org/0000-0003-1060-6412Chao Yang11https://orcid.org/0009-0008-5281-6948State Key Laboratory of Optical Communication Technologies and Networks, China Information Communication Technologies Group Corporation, Wuhan, Hubei, ChinaState Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, ChinaNational Optoelectronics Innovation Center, Wuhan, Hubei, ChinaState Key Laboratory of Optical Communication Technologies and Networks, China Information Communication Technologies Group Corporation, Wuhan, Hubei, ChinaState Key Laboratory of Optical Communication Technologies and Networks, China Information Communication Technologies Group Corporation, Wuhan, Hubei, ChinaState Key Laboratory of Optical Communication Technologies and Networks, China Information Communication Technologies Group Corporation, Wuhan, Hubei, ChinaPeng Cheng Laboratory, Shenzhen, ChinaPeng Cheng Laboratory, Shenzhen, ChinaPeng Cheng Laboratory, Shenzhen, ChinaState Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, ChinaState Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing, ChinaState Key Laboratory of Optical Communication Technologies and Networks, China Information Communication Technologies Group Corporation, Wuhan, Hubei, ChinaThe growing Internet traffic urgently needs large-capacity and cost-effective optical transmissions. To maintain system performance under low-cost conditions, the silicon-based integrated coherent transmit and receive optical sub-assembly (IC-TROSA) and the complex-valued convolutional neural network (CVCNN) algorithm provide an effective solution for high-capacity and long-distance WDM optical transmission. The proposed CVCNN can improve the system performance under nonlinear damage conditions, which fully considers the orthogonality of IQ signals in this paper. This algorithm exhibits different equalization performances for 64QAM signals under various encoding schemes considering 20%-overhead, achieving up to 2dB maximum decrease in the required optical signal-to-noise ratio at the optical back-to-back case. Regarding transmission distance, employing CVCNN extends the maximum reach from 3500 km to 3850 km. The paper also demonstrates the application of CVCNN in WDM systems, enhancing system performance across different WDM encoding schemes. Finally, the experiment verified that CVCNN requires fewer computational resources than real-valued convolutional neural networks (RVCNN).https://ieeexplore.ieee.org/document/10777400/Complex-value neural network800 Gb/s/lane transmissionlong-haul WDMlow-cost optical device |
| spellingShingle | Yuhan Gong Xiaoshuo Jia Ying Zhu Kailai Liu Ming Luo Jin Tao Zhixue He Chao Li Zichen Liu Yan Li Jian Wu Chao Yang Complex-Valued CNN Nonlinear Equalization Enabled 36-Tbit/s (45×800-Gbit/s) WDM Transmission Over 3150 Km Using Silicon-Based IC-TROSA IEEE Photonics Journal Complex-value neural network 800 Gb/s/lane transmission long-haul WDM low-cost optical device |
| title | Complex-Valued CNN Nonlinear Equalization Enabled 36-Tbit/s (45×800-Gbit/s) WDM Transmission Over 3150 Km Using Silicon-Based IC-TROSA |
| title_full | Complex-Valued CNN Nonlinear Equalization Enabled 36-Tbit/s (45×800-Gbit/s) WDM Transmission Over 3150 Km Using Silicon-Based IC-TROSA |
| title_fullStr | Complex-Valued CNN Nonlinear Equalization Enabled 36-Tbit/s (45×800-Gbit/s) WDM Transmission Over 3150 Km Using Silicon-Based IC-TROSA |
| title_full_unstemmed | Complex-Valued CNN Nonlinear Equalization Enabled 36-Tbit/s (45×800-Gbit/s) WDM Transmission Over 3150 Km Using Silicon-Based IC-TROSA |
| title_short | Complex-Valued CNN Nonlinear Equalization Enabled 36-Tbit/s (45×800-Gbit/s) WDM Transmission Over 3150 Km Using Silicon-Based IC-TROSA |
| title_sort | complex valued cnn nonlinear equalization enabled 36 tbit x002f s 45 x00d7 800 gbit x002f s wdm transmission over 3150 km using silicon based ic trosa |
| topic | Complex-value neural network 800 Gb/s/lane transmission long-haul WDM low-cost optical device |
| url | https://ieeexplore.ieee.org/document/10777400/ |
| work_keys_str_mv | AT yuhangong complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa AT xiaoshuojia complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa AT yingzhu complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa AT kailailiu complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa AT mingluo complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa AT jintao complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa AT zhixuehe complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa AT chaoli complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa AT zichenliu complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa AT yanli complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa AT jianwu complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa AT chaoyang complexvaluedcnnnonlinearequalizationenabled36tbitx002fs45x00d7800gbitx002fswdmtransmissionover3150kmusingsiliconbasedictrosa |