Advanced Neural Network-Based Equalization in Intensity-Modulated Direct-Detection Optical Systems: Current Status and Future Trends
Abstract
:1. Introduction
2. Short-Reach IM/DD Systems
2.1. IM/DD System Structure
2.2. IM/DD System Model
3. Performance-Oriented NN-Based Equalizers
3.1. FNN-Based Equalizer
3.2. CNN-Based Equalizer
3.3. RNN-Based Equalizer
3.4. Cascade NN-Based Equalizer
3.5. Other Types of NN-Based Equalizers
3.6. Performance and Complexity Comparison of FNN-, L-RNN-, Cascade FNN-, and AR-RNN-Based Equalizers
3.7. Possible Pitfalls When Applying NN-Based Equalizers
4. Computationally Efficient NN-Based Equalizers
4.1. Transfer Learning
4.2. Pruning
4.3. Multi-Task Learning
4.4. Quantization
5. Conclusions and Future Perspectives
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Cartledge, J.; Karar, A. 100 Gb/s Intensity Modulation and Direct Detection. J. Light. Technol. 2014, 32, 2809–2814. [Google Scholar] [CrossRef]
- Chagnon, M. Optical Communications for Short Reach. J. Light. Technol. 2019, 37, 1779–1797. [Google Scholar] [CrossRef]
- Zhong, K.; Zhou, X.; Huo, J.; Yu, C.; Lu, C.; Lau, A.P.T. Digital Signal Processing for Short-Reach Optical Communications: A Review of Current Technologies and Future Trends. J. Light. Technol. 2018, 36, 377–400. [Google Scholar] [CrossRef]
- Wu, Q.; Xu, Z.; Zhu, Y.; Ji, H.; Yang, Y.; Qiao, G.; Liu, L.; Wang, S.; Liang, J.; Wei, J.; et al. Gradient-Descent Noise Whitening Techniques for Short-Reach IM-DD Optical Interconnects with Severe Bandwidth Limitation. Opt. Express 2024, 32, 1715–1727. [Google Scholar] [CrossRef]
- Xu, Z.; Sun, C.; Manton, J.; Shieh, W. Joint Equalization of Linear and Nonlinear Impairments for PAM4 Short-Reach Direct Detection Systems. IEEE Photon. Technol. Lett. 2021, 33, 425–428. [Google Scholar] [CrossRef]
- Tan, Z.; Yang, C.; Zhu, Y.; Xu, Z.; Zou, K.; Zhang, F.; Wang, Z. A 70 Gbps NRZ Optical Link Based on 850 nm Band-Limited VCSEL for Data-Center Intra-Connects. Sci. China. Info. Sci. 2018, 61, 080406. [Google Scholar] [CrossRef]
- Tan, Z.; Yang, C.; Zhu, Y.; Xu, Z.; Zou, K.; Zhang, F.; Wang, Z. High speed band-limited 850-nm VCSEL link based on time-domain interference elimination. IEEE Photon. Technol. Lett. 2017, 29, 751–754. [Google Scholar] [CrossRef]
- Lu, W.; Liu, Z.; Xu, Z.; Liu, L.; Zou, Y.; Dai, X.; Yang, Q.; Shieh, W. Impact of Non-Gaussian Noise on GMI and LDPC Performance in Neural Network Equalized Systems. Opt. Lett. 2024, 49, 923–926. [Google Scholar] [CrossRef]
- Zhou, J.; Qiao, Y.; Huang, X.; Yu, C.; Cheng, Q.; Tang, X.; Guo, M.; Liu, W.; Li, Z. Joint FDE and MLSD algorithm for 56-Gbit/s optical FTN-PAM4 system using 10G-class optics. J. Light. Technol. 2019, 37, 3343–3350. [Google Scholar] [CrossRef]
- Zhong, K.; Zhou, X.; Wang, Y.; Gui, T.; Yang, Y.; Yuan, J.; Wang, L.; Chen, W.; Zhang, H.; Man, J.; et al. Recent Advances in Short Reach Systems. In Proceedings of the Optical Fiber Communication Conference (OFC), Los Angeles, CA, USA, 19–23 March 2017. [Google Scholar]
- Wu, Q.; Xu, Z.; Zhu, Y.; Ji, H.; Yang, Y.; Liang, J.; Qiao, G.; Wang, S.; Liu, L.; Wei, J.; et al. 405-GBd OOK and 201-GBd PAM-4 IM/DD Optics at Record Faster-Than-Nyquist Ratios of 226.6% and 62.1% Enabled by Advanced Noise Whitening. In Proceedings of the Asia Communications and Photonics Conference (ACP), Wuhan, China, 4–7 November 2023; pp. 1–4. [Google Scholar]
- Xu, X.; Zhou, E.; Liu, G.N.; Zuo, T.; Zhong, Q.; Zhang, L.; Bao, Y.; Zhang, X.; Li, J.; Li, Z. Advanced Modulation Formats for 400-Gbps Short-Reach Optical Inter-Connection. Opt. Express 2015, 1, 492–500. [Google Scholar] [CrossRef]
- Shi, J.; Zhang, J.; Li, X.; Chi, N.; Chang, G.; Yu, J. 112 Gb/s/λ CAP Signals Transmission over 480 km in IM-DD System. In Proceedings of the Optical Fiber Communications Conference (OFC), San Diego, CA, USA, 11–15 March 2018. [Google Scholar]
- Yekani, A.; Rusch, L.A. Interplay of Bit Rate, Linewidth, Bandwidth, and Reach on Optical DMT and PAM with IMDD. IEEE Trans. Commun. 2019, 4, 2908–2913. [Google Scholar] [CrossRef]
- Wu, Q.; Xu, Z.; Zhu, Y.; Ji, T.; Ji, H.; Yang, Y.; Liang, J.; Cheng, C.; Qiao, G.; He, Z.; et al. Beyond 200-Gb/s O-band Intensity Modulation and Direct Detection Optics with Joint Look-Up-Table-Based Predistortion and Digital Resolution Enhancement for Low-Cost Data Center Interconnects. Adv. Photon. Nexus 2024, 3, 036007. [Google Scholar] [CrossRef]
- Liu, N.; Xiao, J.; Liu, C.; Shen, G. IM/DD transmission for Data Center Optical Interconnects. In Proceedings of the Asia Communications and Photonics Conference (ACP), Shanghai, China, 24–27 October 2021. [Google Scholar]
- Jiang, L.; Yan, L.; Yi, A.; Pan, Y.; Zhang, B.; Hu, Q.; Pan, W.; Luo, B. Integrated Components and Solutions for High-Speed Short-Reach Data Transmission. Photonics 2021, 8, 77. [Google Scholar] [CrossRef]
- Wu, Q.; Xu, Z.; Zhu, Y.; Ji, H.; Yang, Y.; Liang, J.; Ji, T.; Qiao, G.; Wang, S.; Liu, L.; et al. Dispersion-Unmanaged Transmission of 144-Gb/s PAM-8 and 110-Gb/s PAM-6 Signals Over 10/20-km SSMF for DML-Based IM-DD Optics at C Band. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 24–28 March 2024. [Google Scholar]
- Wu, Q.; Xu, Z.; Zhu, Y.; Ji, T.; Ji, H.; Yang, Y.; Qiao, G.; Cheng, C.; Tang, J.; Zhao, T.; et al. High-Speed Dispersion-Unmanaged DML-Based IM-DD Optics at C-band with Advanced Nonlinear Equalization and Noise Whitening. J. Light. Technol. 2024, 42, 5591–5598. [Google Scholar] [CrossRef]
- Gao, Y.; Cartledge, J.C.; Yam, S.S.H.; Rezania, A.; Matsui, Y. 112 Gb/s PAM-4 Using a Directly Modulated Laser with Linear Pre-Compensation and Nonlinear Post-Compensation. In Proceedings of the European Conference and Exhibition on Optical Communication (ECOC), Dusseldorf, Germany, 18–22 September 2016. [Google Scholar]
- Zhang, K.; Zhuge, Q.; Xin, H.; Morsy, M.; El-Fiky, E.; Yi, L.; Hu, W.; Plant, D. Intensity Directed Equalizer for the Mitigation of DML Chirp Induced Distortion in Dispersion-Unmanaged C-band PAM Transmission. Opt. Express 2017, 23, 28123–28135. [Google Scholar] [CrossRef]
- Zhang, K.; Zhuge, Q.; Xin, H.; Hu, W.; Plant, D.V. Performance Comparison of DML, EML and MZM in Dispersion-Unmanaged Short Reach Transmissions with Digital Signal Processing. Opt. Express 2018, 26, 34288–34304. [Google Scholar] [CrossRef] [PubMed]
- Stojanovic, N.; Karinou, F.; Qiang, Z.; Prodaniuc, C. Volterra and Wiener Equalizers for Short-Reach 100G PAM-4 Applications. J. Light. Technol. 2017, 21, 4583–4594. [Google Scholar] [CrossRef]
- Watts, P.M.; Mikhailov, V.; Savory, S.; Bayvel, P.; Glick, M.; Lobel, M.; Christensen, B.; Kirkpatrick, P.; Shang, S.; Killey, R.I. Performance of single-mode fiber links using electronic feed-forward and decision feedback equalizers. IEEE Photon. Technol. Lett. 2005, 17, 2206–2208. [Google Scholar] [CrossRef]
- Wang, H.; Zhou, J.; Li, F.; Liu, L.; Yu, C.; Yi, X.; Huang, X.; Liu, W.; Li, Z. Variable-step DD-FTN algorithm for PAM8-based short-reach optical interconnects. In Proceedings of the CLEO: Science and Innovations, San Jose, CA, USA, 5–10 May 2019. [Google Scholar]
- Miao, X.; Bi, M.; Yu, J.; Li, L.; Hu, W. SVM-Modified-FFE Enabled Chirp Management for 10G DML-based 50Gb/s/λ PAM4 IM-DD PON. In Proceedings of the Optical Fiber Communications Conference (OFC), San Diego, CA, USA, 3–7 March 2019. [Google Scholar]
- Tang, X.; Liu, S.; Xu, X.; Qi, J.; Guo, M.; Zhou, J.; Qiao, Y. 50-Gb/s PAM4 over 50-km Single Mode Fiber Transmission Using Efficient Equalization Technique. In Proceedings of the Optical Fiber Communications Conference (OFC), San Diego, CA, USA, 3–7 March 2019. [Google Scholar]
- Zhou, H.; Li, Y.; Liu, Y.; Yue, L.; Gao, C.; Li, W.; Qiu, J.; Guo, H.; Hong, X.; Zuo, Y.; et al. Recent Advances in Equalization Technologies for Short-Reach Optical Links Based on PAM4 Modulation: A Review. Appl. Sci. 2019, 9, 2342. [Google Scholar] [CrossRef]
- Li, D.; Song, H.; Cheng, W.; Deng, L.; Cheng, M.; Fu, S.; Tang, M.; Liu, D. 180 Gb/s PAM8 Signal Transmission in BandwidthLimited IMDD System Enabled by Tap Coefficient Decision Directed Volterra Equalizer. IEEE Access 2020, 8, 19890–19899. [Google Scholar] [CrossRef]
- LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436–444. [Google Scholar] [CrossRef] [PubMed]
- Goodfellow, I.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: London, UK, 2016. [Google Scholar]
- Bishop, C.M. Pattern Recognition and Machine Learning; Springer: New York, NY, USA, 2006. [Google Scholar]
- Schmidhuber, J. Deep learning in neural networks: An overview. Neural Netw. 2015, 61, 85–117. [Google Scholar] [CrossRef]
- Hecht-Nielsen, R. Theory of the backpropagation neural network. In Neural Networks for Perception; Academic Press: Cambridge, MA, USA, 1992; pp. 65–93. [Google Scholar]
- Duchi, J.; Hazan, E.; Singer, Y. Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 2011, 12, 2121–2159. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
- Raich, R.; Zhou, G.T. Orthogonal polynomials for complex Gaussian processes. IEEE Trans. Signal Process. 2004, 52, 2788–2797. [Google Scholar] [CrossRef]
- Domingos, P.M. A few useful things to know about machine learning. Commun. ACM 2012, 55, 78–87. [Google Scholar] [CrossRef]
- Han, S.; Mao, H.; Dally, W.J. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv 2015, arXiv:1510.00149. [Google Scholar]
- Musumeci, F.; Rottondi, C.; Nag, A.; Macaluso, I.; Zibar, D.; Ruffini, M.; Tornatore, M. An overview on application of machine learning techniques in optical networks. IEEE Commun. Surv. Tutor. 2018, 21, 1383–1408. [Google Scholar] [CrossRef]
- Khan, F.N.; Zhou, Y.; Lau, A.P.T.; Lu, C. Modulation Format Identification in Heterogeneous Fiber-Optic Networks Using Artificial Neural Networks. Opt. Express 2012, 20, 12422–12431. [Google Scholar] [CrossRef]
- Zibar, D.; Piels, M.; Jones, R.; Schaeffer, C.G. Machine Learning Techniques in Optical Communication. J. Light. Technol. 2016, 34, 1442–1452. [Google Scholar] [CrossRef]
- Wu, X.; Jargon, J.A.; Skoog, R.A.; Paraschis, L.; Willner, A.E. Applications of Artificial Neural Networks in Optical Performance Monitoring. J. Light. Technol. 2009, 27, 3580–3589. [Google Scholar]
- Tanimura, T.; Hoshida, T.; Kato, T.; Watanabe, S.; Morikawa, H. Data-Analytics-Based Optical Performance Monitoring Technique for Optical Transport Networks. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 11–15 March 2018. [Google Scholar]
- You, Y.; Jiang, Z.; Janz, C. Machine Learning-Based EDFA Gain Model. In Proceedings of the 2018 European Conference on Optical Communication (ECOC), Rome, Italy, 23–27 September 2018. [Google Scholar]
- Morais, R.M.; Pedro, J. Machine Learning Models for Estimating Quality of Transmission in DWDM Networks. J. Opt. Commun. Netw. 2018, 10, D84–D99. [Google Scholar] [CrossRef]
- Yankov, M.; Ros, F.; Moura, U.; Carena, A.; Zibar, D. Flexible Raman Amplifier Optimization Based on Machine Learning-Aided Physical Stimulated Raman Scattering Model. J. Light. Technol. 2017, 35, 1887–1893. [Google Scholar] [CrossRef]
- Panayiotou, T.; Savva, G.; Shariati, B.; Tomkos, I.; Ellinas, G. Machine Learning for QoT Estimation of Unseen Optical Network States. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 3–7 March 2019. [Google Scholar]
- Wang, D.; Zhang, M.; Li, J.; Li, Z.; Li, J.; Song, C.; Chen, X. Intelligent Constellation Diagram Analyzer Using Convolutional Neural Network-Based Deep Learning. Opt. Express 2017, 25, 17150–17166. [Google Scholar] [CrossRef]
- Musumeci, F.; Rottondi, C.E.M.; Corani, G.; Shahkarami, S.; Cugini, F.; Tornatore, M. A Tutorial on Machine Learning for Failure Management in Optical Networks. J. Light. Technol. 2019, 37, 4125–4139. [Google Scholar] [CrossRef]
- Shahkarami, S.; Musumeci, F.; Cugini, F.; Tornatore, M. Machine-Learning-Based Soft-Failure Detection and Identification in Optical Networks. In Proceedings of the Optical Fiber Communications Conference and Exposition (OFC), San Diego, CA, USA, 11–15 March 2018; pp. 1–3. [Google Scholar]
- Khan, F.N.; Fan, Q.; Lu, C.; Lau, A.P.T. An Optical Communication’s Perspective on Machine Learning and Its Applications. J. Light. Technol. 2019, 37, 493–516. [Google Scholar] [CrossRef]
- Zhang, K.; Fan, Y.; Ye, T.; Tao, Z.; Oda, S.; Tanimura, T.; Akiyama, Y.; Hoshida, T. Fiber Nonlinear Noise-to-Signal Ratio Estimation by Machine Learning. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 3–7 March 2019. [Google Scholar]
- Schaedler, M.; Kuschnerov, M.; Pachnicke, S.; Bluemm, C.; Pittala, F.; Changsong, X. Subcarrier Power Loading for Coherent Optical OFDM Optimized by Machine Learning. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 3–7 March 2019. [Google Scholar]
- Wang, C.; Fu, S.; Xiao, Z.; Tang, M.; Liu, D. Long Short-Term Memory Neural Network (LSTM-NN) Enabled Accurate Optical Signal-to-Noise Ratio (OSNR) Monitoring. J. Light. Technol. 2019, 37, 4140–4146. [Google Scholar] [CrossRef]
- Jones, R.; Eriksson, T.; Yankov, M.; Zibar, D. Deep Learning of Geometric Constellation Shaping Including Fiber Nonlinearities. In Proceedings of the 2018 European Conference on Optical Communication (ECOC), Rome, Italy, 23–27 September 2018; pp. 1–3. [Google Scholar]
- Jones, R.; Yankov, M.; Zibar, D. End-to-end learning for GMI optimized geometric constellation shape. In Proceedings of the 2018 European Conference on Optical Communication (ECOC), Dublin, Ireland, 22–26 September 2019; pp. 1–3. [Google Scholar]
- Khan, F.N.; Zhong, K.; Zhou, X.; Al-Arashi, W.H.; Yu, C.; Lu, C.; Lau, A.P.T. Joint OSNR Monitoring and Modulation Format Identification in Digital Coherent Receivers Using Deep Neural Networks. Opt. Express 2017, 25, 17767–17776. [Google Scholar] [CrossRef] [PubMed]
- Tanimura, T.; Hoshida, T.; Kato, T.; Watanabe, S.; Morikawa, H. Convolutional Neural Network-Based Optical Performance Monitoring for Optical Transport Networks. J. Opt. Commun. Netw. 2019, 11, A52–A59. [Google Scholar] [CrossRef]
- Wong, E.; Mondal, S.; Ruan, L. Machine Learning Enhanced Next-Generation Optical Access Networks—Challenges and Emerging Solutions [Invited Tutorial]. J. Opt. Commun. Netw. 2023, 14, A49–A62. [Google Scholar] [CrossRef]
- Rajbhandari, S.; Ghassemlooy, Z.; Angelova, M. Effective denoising and adaptive equalization of indoor optical wireless channel with artificial light using the discrete wavelet transform and artificial neural network. J. Light. Technol. 2009, 27, 4493–4500. [Google Scholar] [CrossRef]
- Haigh, P.A.; Ghassemlooy, Z.; Rajbhandari, S.; Papakonstantinou, I.; Popoola, W. Visible light communications: 170 Mb/s using an artificial neural network equalizer in a low bandwidth white light configuration. J. Light. Technol. 2014, 32, 1807–1813. [Google Scholar] [CrossRef]
- Sorokina, M.; Sergeyev, S.; Turitsyn, S. Fiber echo state network analogue for high-bandwidth dual-quadrature signal processing. Opt. Express 2019, 27, 2387–2395. [Google Scholar] [CrossRef] [PubMed]
- Wu, Q.; Zhu, Y.; Li, X.; Jiang, H.; Cheng, C.; Fu, M.; Zhang, Y.; Zhuge, Q.; Li, Z.; Hu, W. Four-dimensional direct detection receiver enabling Jones-space field recovery with phase and polarization diversity. Photon. Res. 2024, 12, 399–410. [Google Scholar] [CrossRef]
- Chen, G.; Du, J.; Sun, L.; Zhang, W.; Xu, K.; Chen, X.; Reed, G.T.; He, Z. Nonlinear Distortion Mitigation by Machine Learning of SVM Classification for PAM-4 andPAM-8 Modulated Optical Interconnection. J. Light. Technol. 2018, 3, 650–657. [Google Scholar] [CrossRef]
- Chen, G.; Du, J.; Sun, L.; Zheng, L.; Xu, K.; Tsang, H.K.; Chen, X.; Reed, G.T.; He, Z. Machine Learning Adaptive Receiver for PAM-4 Modulated Optical Interconnection Based on Silicon Microring Modulator. J. Light. Technol. 2018, 18, 4106–4113. [Google Scholar] [CrossRef]
- Xie, Y.; Wang, Y.; Kandeepan, S.; Wang, K. Machine Learning Applications for Short Reach Optical Communication. Photonics 2022, 9, 30. [Google Scholar] [CrossRef]
- Ranzini, S.M.; Da Ros, F.; Bülow, H.; Zibar, D. Tunable Optoelectronic Chromatic Dispersion Compensation Based on Machine Learning for Short-Reach Transmission. Appl. Sci. 2019, 9, 4332. [Google Scholar] [CrossRef]
- Chagnon, M.; Karanov, B.; Schmalen, L. Experimental Demonstration of a Dispersion Tolerant End-to-End Deep Learning-Based IM-DD Transmission System. In Proceedings of the European Conference on Optical Communication (ECOC), Roma, Italy, 23–27 September 2018; pp. 1–3. [Google Scholar]
- Younus, O.I.; Hassan, N.B.; Ghassemlooy, Z.; Zvanovec, S.; Alves, L.N.; Le-Minh, H. The Utilization of Artificial Neural Network Equalizer in Optical Camera Communications. Sensors 2021, 21, 2826. [Google Scholar] [CrossRef]
- Jin, R.; Wei, Y.; Zhang, J.; Shi, J.; Chi, N. Neural-Network-Based End-To-End Learning for Adaptive Optimization of Two-Dimensional Signal Generation in UVLC Systems. Opt. Express 2024, 32, 6309–6328. [Google Scholar] [CrossRef]
- Jarajreh, M.A.; Giacoumidis, E.; Aldaya, I.; Le, S.T.; Tsokanos, A.; Ghassemlooy, Z.; Doran, N.J. Artificial Neural Network Nonlinear Equalizer for Coherent Optical OFDM. IEEE Photon. Technol. Lett. 2015, 27, 387–390. [Google Scholar] [CrossRef]
- Wu, Q.; Xu, Z.; Zhu, Y.; Zhang, Y.; Ji, H.; Yang, Y.; Qiao, G.; Liu, L.; Wang, S.; Liang, J.; et al. Machine Learning for Self-Coherent Detection Short-Reach Optical Communications. Photonics 2023, 10, 1001. [Google Scholar] [CrossRef]
- Fang, X.; Chen, X.; Yang, F.; Zhang, L.; Zhang, F. 6.4Tb/s SSB WDM Transmission over 320km SSMF with Linear Network Assisted LSTM. IEEE Photon. Technol. Lett. 2021, 33, 1407–1410. [Google Scholar] [CrossRef]
- Orsuti, D.; Antonelli, C.; Chiuso, A.; Santagiustina, M.; Mecozzi, A.; Galtarossa, A.; Palmieri, L. Deep Learning-Based Phase Retrieval Scheme for Minimum-Phase Signal Recovery. J. Light. Technol. 2023, 41, 578–592. [Google Scholar] [CrossRef]
- An, S.; Zhu, Q.; Li, J.; Ling, Y.; Su, Y. 112-Gb/s SSB 16-QAM signal transmission over 120-km SMF with direct detection using a MIMO-ANN nonlinear equalizer. Opt. Express 2019, 27, 12794–12805. [Google Scholar] [CrossRef] [PubMed]
- Sozos, K.; Deligiannidis, S.; Mesaritakis, C.; Bogris, A. Self-Coherent Receiver Based on a Recurrent Optical Spectrum Slicing Neuromorphic Accelerator. J. Light. Technol. 2023, 41, 2666–2674. [Google Scholar] [CrossRef]
- Chen, Z.; Wang, W.; Zou, D.; Ni, W.; Luo, D.; Li, F. Real-Valued Neural Network Nonlinear Equalization for Long-Reach PONs Based on SSB Modulation. IEEE Photon. Technol. Lett. 2022, 35, 167–170. [Google Scholar] [CrossRef]
- Karanov, B.; Chagnon, M.; Thouin, F.; Eriksson, T.; Bülow, H.; Lavery, D.; Bayvel, P.; Schmalen, L. End-to-End Deep Learning of Optical Fiber Communications. J. Light. Technol. 2018, 36, 4843–4855. [Google Scholar] [CrossRef]
- Karanov, B.; Lavery, D.; Bayvel, P.; Schmalen, L. End-To-End Optimized Transmission over Dispersive Intensity-Modulated Channels Using Bidirectional Recurrent Neural Networks. Opt. Express 2019, 27, 19650–19663. [Google Scholar] [CrossRef]
- Srinivasan, M.; Song, J.; Grabowski, A.; Szczerba, K.; Iversen, H.; Schmidt, M.; Zibar, D.; Schroder, J.; Larsson, A.; Hager, C.; et al. End-to-End Learning for VCSEL-based Optical Interconnects: State-of-the-Art, Challenges, and Opportunities. J. Light. Technol. 2023, 41, 3261–3277. [Google Scholar] [CrossRef]
- Nevin, J.; Nallaperuma, S.; Shevchenko, N.; Li, X.; Faruk, M.; Savory, S. Machine Learning for Optical Fiber Communication Systems: An Introduction and Overview. APL Photon. 2021, 6, 121101. [Google Scholar] [CrossRef]
- Ros, F.; Ranzini, S.; Dischler, R.; Cem, A.; Aref, V.; Bulow, H.; Zibar, D. Machine-Learning-Based Equalization for Short-Reach Transmission: Neural Networks and Reservoir Computing. In Proceedings of the SPIE, Metro and Data Center Optical Networks and Short-Reach Links IV, San Francisco, CA, USA, 6–12 March 2021; p. 1171205. [Google Scholar]
- Kalla, S.; Gagne, C.; Zeng, M.; Rusch, L. Recurrent Neural Networks Achieving MLSE Performance for Optical Channel Equalization. Opt. Express 2021, 29, 13033–13047. [Google Scholar] [CrossRef] [PubMed]
- Schädler, M.; Böcherer, G.; Pachnicke, S. Soft-Demapping for Short Reach Optical Communication: A Comparison of Deep Neural Networks and Volterra Series. J. Light. Technol. 2021, 39, 3095–3105. [Google Scholar] [CrossRef]
- Huang, L.; Jiang, W.; Xu, Y.; Hu, W.; Yi, L. Low-Complexity Volterra-Inspired Neural Network Equalizer in 100-G Band-Limited IMDD PON System. Opt. Lett. 2022, 47, 5692–5695. [Google Scholar] [CrossRef]
- Ahmad, S.T.; Kumar, K.P. Radial basis function neural network nonlinear equalizer for 16-QAM coherent optical OFDM. IEEE Photonics Technol. Lett. 2016, 28, 2507–2510. [Google Scholar] [CrossRef]
- Xu, Z.; Shieh, W. On the Computational Complexity of Artificial Neural Networks for Short-Reach Optical Communication. In Proceedings of the Opto-Electronics and Communications Conference (OECC), Shanghai, China, 2–6 July 2023; pp. 1–4. [Google Scholar]
- Xu, Z.; Sun, C.; Manton, J.; Shieh, W. Computational Complexity Analysis of Neural Network-Based Nonlinear Equalization for Short Reach Direct Detection Systems. In Proceedings of the Asia Communications and Photonics Conference (ACP), Chengdu, China, 2–5 November 2019. [Google Scholar]
- Xu, Z.; Sun, C.; Manton, J.; Shieh, W. Performance and Computational Complexity Evaluation for Neural Network-Based Short-Reach Optical Links. In Proceedings of the Conference on Lasers and Electro-Optics Pacific Rim (CLEO-PR), Sydney, Australia, 2–6 August 2020. [Google Scholar]
- Perin, J.K.; Shastri, A.; Kahn, J.M. Design of Low-Power DSP-Free Coherent Receivers for Data Center Links. J. Light. Technol. 2017, 35, 4650–4662. [Google Scholar] [CrossRef]
- Xu, Z.; Sun, C.; Ji, T.; Manton, J.; Shieh, W. Computational Complexity Comparison of Feedforward/Radial Basis Function/Recurrent Neural Network-Based Equalizer for a 50-Gb/s PAM4 Direct-Detection Optical Link. Opt. Express 2019, 27, 36953–36964. [Google Scholar] [CrossRef]
- Xu, Z.; Sun, C.; Ji, T.; Dong, S.; Zhou, X.; Shieh, W. Investigation on the Impact of Additional Connections to Feedforward Neural Networks for Equalization in PAM4 Short-Reach Direct Detection Links. In Proceedings of the Asia Communications and Photonics Conference (ACP), Beijing, China, 24–27 October 2020. [Google Scholar]
- Zhang, L.; Zhu, Y.; Zhang, F.; Chen, Z. Trends and Enabling Technologies on High-Speed Metro and Short Reach Optical Transmission Systems. Telecommun. Sci. 2019, 35, 62–73. [Google Scholar]
- Estarán, J.; Müller, R.; Mestre, M.; Jorge, F.; Mardoyan, H.; Konczykowska, A.; Dupuy, J.; Bigo, S. Artificial Neural Networks for Linear and Non-linear Impairment Mitigation in High-Baudrate IMDD Systems. In Proceedings of the 2016 European Conference on Optical Communication (ECOC), Düsseldorf, Germany, 18–22 September 2016. [Google Scholar]
- Chuang, C.; Wei, C.; Lin, T.; Chi, K.; Liu, L.; Shi, J.; Chen, Y.; Chen, J. Employing Deep Neural Network for High Speed 4-PAM Optical Interconnect. In Proceedings of the 2017 European Conference on Optical Communication (ECOC), Gothenburg, Sweden, 17–21 September 2017. [Google Scholar]
- Ye, C.; Zhang, D.; Huang, X.; Feng, H.; Zhang, K. Demonstration of 50Gbps IM/DD PAM4 PON over 10GHz Class Optics Using Neural Network Based Nonlinear Equalization. In Proceedings of the 2017 European Conference on Optical Communication (ECOC), Gothenburg, Sweden, 17–21 September 2017. [Google Scholar]
- Reza, A.; Rhee, J. Nonlinear Equalizer Based on Neural Networks for PAM-4 Signal Transmission Using DML. IEEE Photon. Technol. Lett. 2018, 30, 1416–1419. [Google Scholar] [CrossRef]
- Reza, A.; Costas, M.; Browning, C.; Otero, F.; Barry, L. Single-Lane 54-Gbit/s PAM-4/8 Signal Transmissions Using 10G-Class Directly Modulated Lasers Enabled by Low-Complexity Nonlinear Digital Equalization. IEEE Phonton. J. 2022, 14, 7226909. [Google Scholar] [CrossRef]
- Luo, M.; Gao, F.; Li, X.; He, Z.; Fu, S. Transmission of 4×50-Gb/s PAM-4 Signal over 80-km Single Mode Fiber Using Neural Network. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 11–15 March 2018. [Google Scholar]
- Zhang, Q.; Jiang, Y.; Zhou, H.; Deng, C.; Duan, S.; Wang, Z.; Li, Y.; Song, Y.; Chen, J.; Zhang, J.; et al. 137 Gb/s PAM-4 Transmissions at 850 nm over 40 cm Optical Backplane with 25 G Devices with Improved Neural Network-Based Equalization. Appl. Sci. 2019, 9, 5095. [Google Scholar] [CrossRef]
- Ge, L.; Zhang, W.; Zhang, Y.; Liang, C.; Du, J.; He, Z. Compressed Nonlinear Equalizers for Optical Interconnects: Efficiency and Stability. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 8–12 March 2020. [Google Scholar]
- Yi, L.; Liao, T.; Xue, L.; Hu, W. Neural Network-Based Equalization in High-Speed PONs. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 8–12 March 2020. [Google Scholar]
- Kaneda, N.; Zhu, Z.; Chuang, C.; Mahadevan, A.; Farah, B.; Bergman, K.; Veen, D.; Houtsma, V. FPGA Implementation of Deep Neural Network Based Equalizers for High-Speed PON. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 8–12 March 2020. [Google Scholar]
- Zhang, L.; Yang, F.; Ming, H.; Zhu, Y.; Ruan, X.; Li, Y.; Zhang, F. 160-Gb/s Nyquist PAM-4 Transmission with GeSi-EAM Using Artificial Neural Network Based Nonlinear Equalization. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 8–12 March 2020. [Google Scholar]
- Chen, H.; Liu, X.; Fan, Z.; Hu, C.; Zhao, J. Dual-Learning Based Neural Networks for Short-reach Optical Communications. In Proceedings of the Conference on Lasers and Electro-Optics (CLEO), San Jose, CA, USA, 9–14 May 2021. [Google Scholar]
- Chuang, C.; Liu, L.; Wei, C.; Liu, J.; Henrickson, L.; Huang, W.; Wang, C.; Chen, Y.; Chen, J. Convolutional Neural Network based Nonlinear Classifier for 112-Gbps High Speed Optical Link. In Proceedings of the Optical Fiber Communications Conference (OFC), San Diego, CA, USA, 11–15 March 2018. [Google Scholar]
- Li, P.; Yi, L.; Xue, L.; Hu, W. 56 Gbps IM/DD PON based on 10G-Class Optical Devices with 29 dB Loss Budget Enabled by Machine Learning. In Proceedings of the Optical Fiber Communications Conference (OFC), San Diego, CA, USA, 11–15 March 2018. [Google Scholar]
- Yi, L.; Li, P.; Liao, T.; Hu, W. 100Gb/s/λ IM-DD PON Using 20G-class Optical Devices by Machine Learning Based Equalization. In Proceedings of the European Conference and Exhibition on Optical Communication (ECOC), Rome, Italy, 23–27 September 2018. [Google Scholar]
- Li, P.; Yi, L.; Xue, L.; Hu, W. 100Gbps IM/DD Transmission over 25km SSMF using 20Gclass DML and PIN Enabled by Machine Learning. In Proceedings of the Optical Fiber Communications Conference (OFC), San Diego, CA, USA, 11–15 March 2018. [Google Scholar]
- Zhang, J.; Yan, L.; Jiang, L.; Yi, A.; Pan, Y.; Pan, W.; Luo, B. 56-Gbit/s PAM-4 Optical Signal Transmission over 100-km SMF Enabled by TCNN Regression Model. IEEE Photon. J. 2021, 13, 7200606. [Google Scholar] [CrossRef]
- Ye, C.; Zhang, D.; Hu, X.; Huang, X.; Feng, H.; Zhang, K. Recurrent Neural Network (RNN) Based End-to-End Nonlinear Management for Symmetrical 50Gbps NRZ PON with 29dB+ Loss Budget. In Proceedings of the European Conference and Exhibition on Optical Communication (ECOC), Rome, Italy, 23–27 September 2018. [Google Scholar]
- Huang, X.; Zhang, D.; Hu, X.; Ye, C.; Zhang, K. Recurrent Neural Network Based Equalizer with Embedded Parallelization for 100Gbps/λ PON. In Proceedings of the Optical Fiber Communication Conference (OFC), San Francisco, CA, USA, 6–10 June 2021. [Google Scholar]
- Huang, X.; Zhang, D.; Hu, X.; Ye, C.; Zhang, K. Low-Complexity Recurrent Neural Network Based Equalizer with Embedded Parallelization for 100-Gbit/s/λ PON. J. Light. Technol. 2022, 40, 1353–1359. [Google Scholar] [CrossRef]
- Zhou, Q.; Yang, C.; Liang, A.; Zheng, X.; Chen, Z. Low Computationally Complex Recurrent Neural Network for High Speed Optical Fiber Transmission. Opt. Commun. 2019, 441, 121–126. [Google Scholar] [CrossRef]
- Yang, C.; Gao, Y.; Wang, J.; Li, H.; Hasnain, C. Enhanced Recurrent Neural Network Equalization Based on Hidden Feature Extraction Learning for Optical Interconnect. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 24–28 March 2024. [Google Scholar]
- Dai, X.; Li, X.; Luo, M.; You, Q.; Yu, S. LSTM Networks Enabled Nonlinear Equalization in 50-Gb/s PAM4 Transmission Links. Appl. Opt. 2019, 58, 6079–6084. [Google Scholar] [CrossRef] [PubMed]
- Peng, C.; Chan, D.; Tong, Y.; Chow, C.; Liu, Y.; Yeh, C.; Tsang, H. Long Short-Term Memory Neural Network for Mitigating Transmission Impairments of 160 Gbit/s PAM4 Microring Modulation. In Proceedings of the Optical Fiber Communication Conference (OFC), San Francisco, CA, USA, 6–10 June 2021. [Google Scholar]
- Peng, C.; Chan, D.; Chow, C.; Hung, T.; Jian, Y.; Tong, Y.; Kuo, P.; Chen, G.; Liu, Y.; Yeh, C.; et al. Long Short Term Memory Neural Network (LSTMNN) and Inter-Symbol Feature Extraction for 160 Gbit/s PAM4 from Silicon Micro-Ring Transmitter. Opt. Commun. 2023, 529, 129067. [Google Scholar] [CrossRef]
- Hung, T.; Chan, D.; Peng, C.; Chow, C.; Yeh, C.; Tsang, H. 300-Gbit/s/λ PAM8 Modulation with a Silicon Microring Modulator using Long Short Term Memory Regression and Deep Neural Network Classification. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 24–28 March 2024. [Google Scholar]
- Sang, B.; Zhang, J.; Wang, C.; Kong, M.; Tan, Y.; Zhao, L.; Zhou, W.; Shang, D.; Zhu, Y.; Yi, H.; et al. Multi-Symbol Output Long Short-Term Memory Neural Network Equalizer for 200+ Gbps IM/DD System. In Proceedings of the European Conference and Exhibition on Optical Communication (ECOC), Bordeaux, France, 13–16 September 2021. [Google Scholar]
- Sang, B.; Zhou, W.; Tan, Y.; Kong, M.; Wang, C.; Wang, M.; Zhao, L.; Zhang, J.; Yu, J. Low Complexity Neural Network Equalization Based on Multi-Symbol Output Technique for 200+ Gbps IM/DD Short Reach Optical System. J. Light. Technol. 2022, 40, 2890–2900. [Google Scholar] [CrossRef]
- Murphy, S.; Townsend, P.; Antony, C. Recurrent Neural Network Equalizer to Extend Input Power Dynamic Range of SOA in 100Gb/s/λ PON. In Proceedings of the Conference on Lasers and Electro-Optics (CLEO), San Jose, CA, USA, 15–20 May 2022. [Google Scholar]
- Murphy, S.; Jamali, F.; Townsend, P.; Antony, C. High Dynamic Range 100 Gbit/s PAM4 PON with SOA Preamplifier using Gated Recurrent Neural Network Equaliser. In Proceedings of the European Conference and Exhibition on Optical Communication (ECOC), Basel, Switzerland, 18–22 September 2022. [Google Scholar]
- Xu, Z.; Sun, C.; Ji, T.; Ji, H.; Manton, J.; Shieh, W. Cascade Recurrent Neural Network Enabled 100-Gb/s PAM4 Short-Reach Optical Link Based on DML. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 8–12 March 2020. [Google Scholar]
- Xu, Z.; Sun, C.; Ji, T.; Manton, J.; Shieh, W. Cascade Recurrent Neural Network Assisted Nonlinear Equalization for a 100 Gb/s PAM4 Short-Reach Direct Detection System. Opt. Lett. 2020, 45, 4216–4219. [Google Scholar] [CrossRef] [PubMed]
- Murphy, S.; Jamali, F.; Townsend, P.; Antony, C. Adaptive Neural Network Equalisation Using Skip Connections for Future 100 Gbit/s/λ Passive Optical Networks. In Proceedings of the 2023 European Conference on Optical Communication (ECOC), Glasgow, Scotland, 1–5 October 2023. [Google Scholar]
- Yang, Z.; Gao, F.; Fu, S.; Li, X.; Deng, L.; He, Z.; Tang, M.; Liu, D. Radial Basis Function Neural Network Enabled C-band 4 × 50 Gb/s PAM-4 Transmission over 80 km SSMF. Opt. Lett. 2018, 15, 3542–3545. [Google Scholar] [CrossRef]
- Arnold, E.; Bocherer, G.; Muller, E.; Spilger, P.; Schemmel, J.; Calabro, S.; Kuschnerov, M. Spiking Neural Network Equalization on Neuromorphic Hardware for IM/DD Optical Communication. In Proceedings of the European Conference and Exhibition on Optical Communication (ECOC), Basel, Switzerland, 18–22 September 2022. [Google Scholar]
- Arnold, E.; Bocherer, G.; Strasser, F.; Muller, E.; Spilger, P.; Billaudelle, S.; Weis, J.; Schemmel, J.; Calabro, S.; Kuschnerov, M. Spiking Neural Network Nonlinear Demapping on Neuromorphic Hardware for IM/DD Optical Communication. J. Light. Technol. 2023, 41, 3424–3431. [Google Scholar] [CrossRef]
- Bocherer, G.; Strasser, F.; Arnold, E.; Lin, Y.; Schemmel, J.; Calabro, S.; Kuschnerov, M. Spiking Neural Network Linear Equalization: Experimental Demonstration of 2km 100Gb/s IM/DD PAM4 Optical Transmission. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 5–9 March 2023. [Google Scholar]
- Bocherer, G. Spiking Neural Network Equalization: Towards Evaluation of Throughput and Power Consumption. In Proceedings of the 2023 European Conference on Optical Communication (ECOC), Glasgow, Scotland, 1–5 October 2023. [Google Scholar]
- Bank, A.; Edelmann, E.; Schmalen, S. Energy-Efficient Spiking Neural Network Equalization for IM/DD Systems with Optimized Neural Encoding. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 24–28 March 2024. [Google Scholar]
- Taniguchi, H.; Yamamoto, S.; Masuda, A.; Kisaka, Y.; Kanazawa, S. 800-Gbps PAM-4 2-km Transmission using 4-λ LAN-WDM TOSA with MLSE based on Deep Neural Network. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 6–10 March 2022. [Google Scholar]
- Yan, A.; Xing, S.; Li, G.; Li, Z.; Luo, P.; Sun, A.; Shi, J.; Zhang, H.; Xiao, X.; He, Z.; et al. 140-Gbaud PAM-8 IM/DD Transmission and FTN Signal Processing based on Low-Complexity Nonlinear M-BCJR Equalization with Deep Neural-Network Channel Model. In Proceedings of the 2023 European Conference on Optical Communication (ECOC), Glasgow, Scotland, 1–5 October 2023. [Google Scholar]
- Bluemm, C.; Liu, B.; Li, B.; Rahman, T.; Hossain, M.; Schaedler, M.; Schlichtmann, U.; Kuschnerov, M.; Calabrò, S. 800Gb/s PAM4 Transmission over 10km SSMF Enabled by Low-complex Duobinary Neural Network Equalization. In Proceedings of the European Conference and Exhibition on Optical Communication (ECOC), Basel, Switzerland, 18–22 September 2022. [Google Scholar]
- Bluemm, C.; Liu, B.; Li, B.; Rahman, T.; Hossain, M.; Schaedler, M.; Schlichtmann, U.; Kuschnerov, M.; Calabrò, S. Hardware-Efficient Duobinary Neural Network Equalizers for 800 Gb/s IM/DD PAM4 Transmission Over 10 km SSMF. J. Light. Technol. 2023, 41, 3783–3790. [Google Scholar] [CrossRef]
- Yan, A.; Xing, S.; Li, Z.; Li, G.; Sun, A.; Luo, P.; Shi, J.; Zhang, H.; Wang, D.; Xiao, X.; et al. Adaptive Partial-Response Neural Network Equalization for Bandwidth-limited PAM Transmission in Intra-Datacenter Interconnect. J. Light. Technol. 2024, 42, 2762–2773. [Google Scholar] [CrossRef]
- Eriksson, T.; Bülow, H.; Leven, A. Applying Neural Networks in Optical Communication Systems: Possible Pitfalls. IEEE Photon. Technol. Lett. 2017, 29, 2091–2094. [Google Scholar] [CrossRef]
- Shu, L.; Li, J.; Wan, Z.; Zhang, W.; Fu, S.; Xu, K. Overestimation Trap of Artificial Neural Network: Learning the Rule of PRBS. In Proceedings of the European Conference and Exhibition on Optical Communication (ECOC), Rome, Italy, 23–27 September 2018. [Google Scholar]
- Chuang, C.; Liu, L.; Wei, C.; Liu, J.; Henrickson, L.; Wang, C.; Chen, Y.; Chen, J. Study of Training Patterns for Employing Deep Neural Networks in Optical Communication Systems. In Proceedings of the European Conference and Exhibition on Optical Communication (ECOC), Rome, Italy, 23–27 September 2018. [Google Scholar]
- Liao, T.; Xue, L.; Huang, L.; Hu, W.; Yi, L. Training Data Generation and Validation for a Neural Network-Based Equalizer. Opt. Lett. 2020, 45, 5113–5116. [Google Scholar] [CrossRef] [PubMed]
- Kim, J.; Kim, H. PRBS Orders Required to Train ANN Equalizer for PAM Signal without Overfitting. Opt. Express 2022, 30, 25486–25497. [Google Scholar] [CrossRef]
- Pan, S.; Yang, Q. A Survey on Transfer Learning. IEEE Trans. Knowl. Data Eng. 2010, 22, 1345–1359. [Google Scholar] [CrossRef]
- Xia, L.; Zhang, J.; Hu, S.; Zhu, M.; Song, Y.; Qiu, K. Transfer Learning Assisted Deep Neural Network for OSNR Estimation. Opt. Express 2019, 27, 19398–19406. [Google Scholar] [CrossRef]
- Azzimonti, D.; Rottondi, C.; Giusti, A.; Tornatore, M.; Bianco, A. Active vs Transfer Learning Approaches for QoT Estimation with Small Training Datasets. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 8–12 March 2020. [Google Scholar]
- Wang, D.; Xu, Y.; Li, J.; Zhang, M.; Li, J.; Qin, J.; Ju, C.; Zhang, Z.; Chen, X. Comprehensive Eye Diagram Analysis: A Transfer Learning Approach. IEEE Phonton. J. 2019, 11, 7205019. [Google Scholar] [CrossRef]
- Zhang, J.; Xia, L.; Zhu, M.; Hu, S.; Xu, B.; Qiu, K. Fast Remodeling for Nonlinear Distortion Mitigation Based on Transfer Learning. Opt. Lett. 2019, 44, 4243–4246. [Google Scholar] [CrossRef]
- Zhang, J.; Xu, T.; Jin, T.; Jiang, W.; Hu, S.; Huang, X.; Xu, B.; Yu, Z.; Yi, X.; Qiu, K. Meta-Learning Assisted Source Domain Optimization for Transfer Learning Based Optical Fiber Nonlinear Equalization. J. Light. Technol. 2023, 41, 1269–1277. [Google Scholar] [CrossRef]
- Freire, P.; Abode, D.; Prilepsky, J.; Costa, N.; Spinnler, B.; Napoli, A.; Turitsyn, S. Transfer Learning for Neural Networks-Based Equalizers in Coherent Optical Systems. J. Light. Technol. 2021, 39, 6733–6745. [Google Scholar] [CrossRef]
- Freire, P.; Spinnler, B.; Abode, D.; Prilepsky, J.; Ali, A.; Costa, N.; Schairer, W.; Napoli, A.; Ellis, A.; Turitsyn, S. Domain Adaptation: The Key Enabler of Neural Network Equalizers in Coherent Optical Systems. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 6–10 March 2022. [Google Scholar]
- Xu, Z.; Sun, C.; Ji, T.; Ji, H.; Manton, J.; Shieh, W. Transfer Learning Aided Neural Networks for Nonlinear Equalization in Short-Reach Direct Detection Systems. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 8–12 March 2020. [Google Scholar]
- Xu, Z.; Sun, C.; Ji, T.; Manton, J.; Shieh, W. Feedforward and Recurrent Neural Network-Based Transfer Learning for Nonlinear Equalization in Short-Reach Optical Links. J. Light. Technol. 2021, 39, 475–480. [Google Scholar] [CrossRef]
- Liu, X.; Li, J.; Fan, Z.; Zhao, J. Transfer-Learning Based Convolutional Neural Network for Short-Reach Optical Interconnects. In Proceedings of the Asia Communications and Photonics Conference (ACP), Shanghai, China, 24–27 October 2021. [Google Scholar]
- Xiao, J.; Sun, L.; Liu, C.; Mao, B.; Liu, G. Fastly Converged Transfer Learning Using Neuron-Pruning Nonlinear Equalizer for Intra Data Center Networking. In Proceedings of the Opto-Electronics and Communications Conference (OECC), Toyama, Japan, 3–6 July 2022. [Google Scholar]
- Xiao, J.; Sun, L.; Liu, C.; Liu, G. Optimizations and Investigations for Transfer Learning of Iteratively Pruned Neural Network Equalizers for Data Center Networking. Opt. Express 2022, 30, 36358–36367. [Google Scholar] [CrossRef]
- Huang, W.; Chang, W.; Wei, C.; Liu, J.; Chen, Y.; Chi, K.; Wang, C.; Shi, J.; Chen, J. 93% Complexity Reduction of Volterra Nonlinear Equalizer by L1-Regularization for 112-Gbps PAM-4 850-nm VCSEL Optical Interconnect. In Proceedings of the Optical Fiber Communications Conference (OFC), San Diego, CA, USA, 11–15 March 2018. [Google Scholar]
- Ge, L.; Zhang, W.; Liang, C.; He, Z. Threshold based Pruned Retraining Volterra Equalization for PAM-4 100 Gbps VCSEL and MMF Based Optical Interconnects. In Proceedings of the Asia Communications and Photonics Conference (ACP), Hangzhou, China, 26–29 October 2018. [Google Scholar]
- Chuang, C.; Chang, W.; Wei, C.; Ho, C.; Huang, C.; Shi, J.; Henrickson, L.; Chen, Y.; Chen, J. Sparse Volterra Nonlinear Equalizer by Employing Pruning Algorithm for High-Speed PAM-4 850-nm VCSEL Optical Interconnect. In Proceedings of the Optical Fiber Communications Conference (OFC), San Diego, CA, USA, 3–7 March 2019. [Google Scholar]
- Yadav, G.; Chuang, C.; Feng, K.; Yan, J.; Chen, J.; Chen, Y. Reducing Computation Complexity by Using Elastic Net Regularization Based Pruned Volterra Equalization in a 80 Gbps PAM-4 Signal for Inter-Data Center Interconnects. Opt. Express 2020, 28, 38539–38552. [Google Scholar] [CrossRef] [PubMed]
- Fujisawa, S.; Yaman, F.; Batshon, H.; Tanio, M.; Ishii, N.; Huang, C.; Lima, T.; Inada, Y.; Prucnal, P.; Kamiya, N.; et al. Weight Pruning Techniques Towards Photonic Implementation of Nonlinear Impairment Compensation Using Neural Networks. J. Light. Technol. 2022, 40, 1273–1282. [Google Scholar] [CrossRef]
- Wan, Z.; Li, J.; Shu, L.; Luo, M.; Li, X.; Fu, S.; Xu, K. Nonlinear Equalization Based on Pruned Artificial Neural Networks for 112-Gb/s SSB-PAM4 Transmission over 80-km SSMF. Opt. Express 2018, 8, 10631–10642. [Google Scholar] [CrossRef] [PubMed]
- Ge, L.; Zhang, W.; Liang, C.; He, Z. Compressed Neural Network Equalization Based on Iterative Pruning Algorithm for 112-Gbps VCSEL-Enabled Optical Interconnects. J. Light. Technol. 2020, 38, 1323–1329. [Google Scholar] [CrossRef]
- Li, M.; Zhang, W.; Chen, Q.; He, Z. High-Throughput Hardware Deployment of Pruned Neural Network Based Nonlinear Equalization for 100-Gbps Short-Reach Optical Interconnect. Opt. Lett. 2021, 46, 4980–4983. [Google Scholar] [CrossRef]
- Xu, Z.; Dong, S.; Jiang, C.; Manton, J.; Shieh, W. Sparsely-Connected Cascade Recurrent Neural Network-Based Nonlinear Equalizer for a 100-Gb/s PAM4 Optical Interconnect. In Proceedings of the Asia Communications and Photonics Conference (ACP), Shanghai, China, 24–27 October 2021. [Google Scholar]
- Yadav, G.; Chuang, C.; Feng, K.; Chen, J.; Chen, Y. Computation Efficient Sparse DNN Nonlinear Equalization for IM/DD 112 Gbps PAM4 Inter-Data Center Optical Interconnects. Opt. Lett. 2021, 46, 1999–2002. [Google Scholar] [CrossRef]
- Yadav, G.; Chuang, C.; Feng, K.; Chen, J.; Chen, Y. Sparsity Learning Deep Neural Network Nonlinear Equalization Method for 112Gbps PAM4 Short-Reach Transmission Links. J. Light. Technol. 2023, 41, 2333–2342. [Google Scholar] [CrossRef]
- Kaneda, N.; Chuang, C.; Zhu, Z.; Mahadevan, A.; Farah, B.; Bergman, K.; Veen, D.; Houtsma, V. Fixed-Point Analysis and FPGA Implementation of Deep Neural Network Based Equalizers for High-Speed PON. J. Light. Technol. 2022, 40, 1972–1980. [Google Scholar] [CrossRef]
- Xu, Z.; Sun, C.; Dong, S.; Manton, J.H.; Shieh, W. Towards Low Computational Complexity for Neural Network-Based Equalization in PAM4 Short-Reach Direct Detection Systems by Multi-Symbol Prediction. In Proceedings of the Optical Fiber Communication Conference (OFC), San Francisco, CA, USA, 6–10 June 2021. [Google Scholar]
- Xu, Z.; Dong, S.; Manton, J.; Shieh, W. Low-Complexity Multi-Task Learning Aided Neural Networks for Equalization in Short-Reach Optical Interconnects. J. Light. Technol. 2022, 40, 45–54. [Google Scholar] [CrossRef]
- Osadchuk, Y.; Jovanovic, O.; Zibar, D.; Ros, F. Reservoir Computing-based Multi-Symbol Equalization for PAM 4 Short-reach Transmission. In Proceedings of the Conference on Lasers and Electro-Optics (CLEO), San Jose, CA, USA, 7–12 May 2023. [Google Scholar]
- Osadchuk, Y.; Jovanovic, O.; Zibar, D.; Ros, F. Multi-Symbol Reservoir Computing-Based Equalization for PAM-4 IM/DD Transmission. IEEE Photon. Technol. Lett. 2024, 36, 853–856. [Google Scholar] [CrossRef]
- Xu, Z.; Dong, S.; Ji, H.; Manton, J.H.; Shieh, W. Computationally-Efficient Sparsely-Connected Multi-Output Neural Networks for IM/DD System Equalization. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 6–10 March 2022. [Google Scholar]
- Liu, B.; Bluemm, C.; Calabro, S.; Li, B.; Schlichtmann, U. Area-Efficient Neural Network CD Equalizer for 4 × 200Gb/s PAM4 CWDM4 Systems. In Proceedings of the Optical Fiber Communication Conference (OFC), San Diego, CA, USA, 5–9 March 2023. [Google Scholar]
- Liu, B.; Bluemm, C.; Calabro, S.; Li, B.; Schlichtmann, U. Area-Efficient Hardware Parallelization of Neural Network CD Equalizers for 4×200 Gb/s PAM4 CWDM4 Systems. In Proceedings of the 2023 European Conference on Optical Communication (ECOC), Glasgow, Scotland, 1–5 October 2023. [Google Scholar]
- Ron, D.; Freire, P.; Prilepsky, J.; Kopae, M.; Napoli, A.; Turitsyn, K. Experimental Implementation of a Neural Network Optical Channel Equalizer in Restricted Hardware Using Pruning and Quantization. Sci. Rep. 2022, 12, 8713. [Google Scholar] [CrossRef] [PubMed]
- Darweesh, J.; Costa, N.; Napoli, A.; Spinnler, B.; Jaouen, Y.; Yousefi, M. Few-bit Quantization of Neural Networks for Nonlinearity Mitigation in a Fiber Transmission Experiment. In Proceedings of the European Conference and Exhibition on Optical Communication (ECOC), Basel, Switzerland, 18–22 September 2022. [Google Scholar]
- Freire, P.; Napoli, A.; Spinnler, B.; Anderson, M.; Ron, D.; Schairer, W.; Bex, T.; Costa, N.; Turitsyn, S.; Prilepsky, J. Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation. J. Light. Technol. 2023, 41, 4557–4581. [Google Scholar] [CrossRef]
- Akino, T.; Wang, Y.; Kojima, K.; Parsons, K.; Yoshida, T. Zero-Multiplier Sparse DNN Equalization for Fiber-Optic QAM Systems with Probabilistic Amplitude Shaping. In Proceedings of the European Conference and Exhibition on Optical Communication (ECOC), Bordeaux, France, 13–16 September 2021. [Google Scholar]
- Xu, Z.; Ji, H.; Yang, Y.; Qiao, G.; Wu, Q.; Li, J.; Lu, W.; Liu, L.; Wang, S.; Wei, J.; et al. Mixed-Precision Integer-Arithmetic-Only Neural Network-Based Equalizers for DML-Based Short-Reach IM/DD Systems. In Proceedings of the 2023 European Conference on Optical Communication (ECOC), Glasgow, Scotland, 1–5 October 2023. [Google Scholar]
- Xu, Z.; Ji, H.; Yang, Y.; Qiao, G.; Wu, Q.; Lu, W.; Liu, L.; Wang, S.; Liang, J.; Li, J.; et al. Quantization of Recurrent Neural Network for Low-Complexity High-Speed IM/DD System Equalization Based on Neuron Clustering. In Proceedings of the Asia Communications and Photonics Conference (ACP), Wuhan, China, 4–7 November 2023; pp. 1–4. [Google Scholar]
- Xu, Z.; Wu, Q.; Lu, W.; Ji, H.; Chen, H.; Ji, T.; Yang, Y.; Qiao, G.; Tang, J.; Cheng, C.; et al. Weight-Adaptive Joint Mixed-Precision Quantization and Pruning for Neural Network-Based Equalization in Short-Reach Direct Detection Links. Opt. Lett. 2024, 49, 3500–3503. [Google Scholar] [CrossRef]
NN Type | Ref. | Modulation | Data Rate | Fiber Length | Tx Type | Wavelength |
---|---|---|---|---|---|---|
FNN | [95] | PAM4 | 168 Gb/s | 1.5 km SMF | MZM (35 GHz) | ~1550 nm |
[96] | PAM4 | 64 Gb/s | 4 km MMF | VCSEL (25 GHz) | ~850 nm | |
[97] | PAM4 | 50 Gb/s | 20 km SMF | MZM (10 GHz) | ~1550 nm | |
[98] | PAM4 | 20 Gb/s | 18 km SMF | DML (10 GHz) | ~1310 nm | |
[99] | PAM2/PAM4/PAM8 | 54 Gb/s | 25 km SMF | DML (10 GHz) | ~1550 nm | |
[100] | PAM4 | 4 × 50 Gb/s | 80 km SMF | DML (20 GHz) | ~1550 nm | |
[101] | PAM4 | 137 Gb/s | 40 cm MMF | MZM (25 GHz) | ~850 nm | |
[102] | PAM4 | 112 Gb/s | 100 m MMF | VCSEL (NA) | ~850 nm | |
[103] | PAM4 | 50 Gb/s | 20 km SMF | DML (10 GHz) | ~1310 nm | |
[104] | PAM2 | 50 Gb/s | 30 km SMF | MZM (35 GHz) | ~1310 nm | |
[105] | PAM4 | 160 Gb/s | 2 km SMF | GeSi EAM (30 GHz) | ~1550 nm | |
[106] | PAM4 | 56 Gb/s | 20/30/40 km SMF | MZM (40 GHz) | ~1550 nm | |
CNN | [107] | PAM4 | 112 Gb/s | 40 km SMF | EML (25 GHz) | ~1310 nm |
[108] | PAM4 | 56 Gb/s | 25 km SMF | DML (10 GHz) | ~1310 nm | |
[109,110] | PAM8/PAM16 | 100 Gb/s | 25 km SMF | DML (20 GHz) | ~1310/1550 nm | |
[111] | PAM4 | 56 Gb/s | 100 km SMF | MZM (40 GHz) | ~1550 nm | |
RNN | [112] | PAM2/PAM4 | 60/100 Gb/s | 20 km SMF | MZM (40 GHz) | ~1550 nm |
[113,114] | PAM4 | 100 Gb/s | 20 km SMF | MZM (NA) | ~1310 nm | |
[115] | PAM4 | 56 Gb/s | 100 m MMF | VCSEL (18 GHz) | ~850 nm | |
[116] | PAM8 | 288 Gb/s | 100 m MMF | VCSEL (23 GHz) | ~850 nm | |
[117] | PAM4 | 50 Gb/s | 100 km SMF | DML (18 GHz) | ~1550 nm | |
[118,119] | PAM4 | 160 Gb/s | 1 km SMF | Si MRM (47 GHz) | ~1550 nm | |
[120] | PAM8 | 270 Gb/s | 1 km SMF | Si MRM (55 GHz) | ~1550 nm | |
[121,122] | PAM4 | 212 Gb/s | 1 km NZDSF | EML (40 GHz) | ~1550 nm | |
[123,124] | PAM4 | 100 Gb/s | 5.4 km SMF | MZM (NA) | ~1550 nm | |
Cascade NN | [125,126] | PAM4 | 50/100 Gb/s | 25/15 km SMF | DML (16 GHz) | ~1550 nm |
[127] | PAM4 | 100 Gb/s | 4.8 km SMF | MZM (33 GHz) | ~1550 nm | |
RBF-NN | [128] | PAM4 | 4 × 50 Gb/s | 80 km SMF | DML (18 GHz) | ~1550 nm |
SNN | [129,130] | PAM4 | 224 Gb/s | 4 km SMF | NA | ~1270 nm |
[131,132] | PAM4 | 100 Gb/s | 2 km SMF | NA | ~1310 nm | |
[133] | PAM4 | 200 Gb/s | 5 km SMF | NA | ~1270 nm |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Xu, Z.; Ji, T.; Wu, Q.; Lu, W.; Ji, H.; Yang, Y.; Qiao, G.; Tang, J.; Cheng, C.; Liu, L.; et al. Advanced Neural Network-Based Equalization in Intensity-Modulated Direct-Detection Optical Systems: Current Status and Future Trends. Photonics 2024, 11, 702. https://doi.org/10.3390/photonics11080702
Xu Z, Ji T, Wu Q, Lu W, Ji H, Yang Y, Qiao G, Tang J, Cheng C, Liu L, et al. Advanced Neural Network-Based Equalization in Intensity-Modulated Direct-Detection Optical Systems: Current Status and Future Trends. Photonics. 2024; 11(8):702. https://doi.org/10.3390/photonics11080702
Chicago/Turabian StyleXu, Zhaopeng, Tonghui Ji, Qi Wu, Weiqi Lu, Honglin Ji, Yu Yang, Gang Qiao, Jianwei Tang, Chen Cheng, Lulu Liu, and et al. 2024. "Advanced Neural Network-Based Equalization in Intensity-Modulated Direct-Detection Optical Systems: Current Status and Future Trends" Photonics 11, no. 8: 702. https://doi.org/10.3390/photonics11080702