Multiparameter performance monitoring of pulse amplitude modulation channels using convolutional neural networks

Si-Ao Li; Yuanpeng Liu; Yiwen Zhang; Wenqian Zhao; Tongying Shi; Xiao Han; Ivan B. Djordjevic; Changjing Bao; Zhongqi Pan; Yang Yue

doi:10.1117/1.APN.3.2.026009

[1] X. Zhou, R. Urata, H. Liu. Beyond 1 Tb/s intra-data center interconnect technology: IM-DD OR coherent?. J. Lightwave Technol., 38, 475-484(2020).

[2] E. Maniloff, S. Gareau, M. Moyer. 400G and beyond: coherent evolution to high-capacity inter data center links, M3H.4(2019).

[3] Q. Cheng et al. Recent advances in optical technologies for data centers: a review. Optica, 5, 1354-1370(2018).

[4] S. T. Le et al. Beyond 400 Gb/s direct detection over 80 km for data center interconnect applications. J. Lightwave Technol., 38, 538-545(2020).

[5] Z. Qu et al. Single-lambda 100G-PAM4 QSFP28 transceiver for 80-km C-band transmission. Proc. SPIE, 11038, 1130806(2020).

[6] S.-R. Moon et al. Realization of real-time DSP for C-band PAM-4 transmission in inter-datacenter network. Opt. Express, 28, 1269-1278(2020).

[7] N. Eiselt et al. Evaluation of real-time 8×56.25 Gb/s (400G) PAM-4 for inter-data center application over 80 km of SSMF at 1550 nm. J. Lightwave Technol., 35, 955-962(2016).

[8] H. Mardoyan et al. 84-, 100-, and 107-GBd PAM-4 intensity-modulation direct-detection transceiver for datacenter interconnects. J. Lightwave Technol., 35, 1253-1259(2017).

[9] M. Chagnon. Direct-detection technologies for intra-and inter-data center optical links, W1F.4(2019).

[10] A. Mecozzi, M. Shtaif. Information capacity of direct detection optical transmission systems. J. Lightwave Technol., 36, 689-694(2017).

[11] Inphi Corporation.

[12] D. Zou et al. 100G PAM-6 and PAM-8 signal transmission enabled by pre-chirping for 10-km intra-DCI utilizing MZM in C-band. J. Lightwave Technol., 38, 3445-3453(2020).

[13] H. Xin et al. 120 GBaud PAM-4/PAM-6 generation and detection by photonic aided digital-to-analog converter and linear equalization. J. Lightwave Technol., 38, 2226-2230(2020).

[14] J. Zhang et al. 280 Gb/s IM/DD PS-PAM-8 transmission over 10 km SSMF at O-band for optical interconnects, M4F.1(2020).

[15] T. A. Eriksson et al. 56 Gbaud probabilistically shaped PAM8 for data center interconnects(2017).

[16] R. A. Linke, A. H. Gnauck. High-capacity coherent lightwave systems. J. Lightwave Technol., 6, 1750-1769(1988).

[17] D.-S. Ly-Gagnon et al. Coherent detection of optical quadrature phase-shift keying signals with carrier phase estimation. J. Lightwave Technol., 24, 12-21(2006).

[18] M. Morsy-Osman, D. V. Plant. A comparative study of technology options for next generation intra- and inter-datacenter interconnects, W4E.1(2019).

[19] J. Wei et al. System aspects of the next-generation data-center networks based on 200G per lambda IMDD links. Proc. SPIE, 11308, 1130805(2020).

[20] E. El-Fiky et al. 400 Gb/s O-band silicon photonic transmitter for intra-datacenter optical interconnects. Opt. Express, 27, 10258-10268(2019).

[21] A. Nag, M. Tornatore, B. Mukherjee. Optical network design with mixed line rates and multiple modulation formats. J. Lightwave Technol., 28, 466-475(2009).

[22] W. Wei, C. Wang, J. Yu. Cognitive optical networks: key drivers, enabling techniques, and adaptive bandwidth services. IEEE Commun. Mag., 50, 106-113(2012).

[23] Q. Cai et al. Modulation format identification in fiber communications using single dynamical node-based photonic reservoir computing. Photonics Res., 9, B1-B8(2021).

[24] X. Han et al. Joint probabilistic-Nyquist pulse shaping for an LDPC-coded 8-PAM signal in DWDM data center communications. Appl. Sci., 9, 4996(2019).

[25] M. Zhu et al. Optical single side-band Nyquist PAM-4 transmission using dual-drive MZM modulation and direct detection. Opt. Express, 26, 6629-6638(2018).

[26] K. Wang et al. High-speed PS-PAM8 transmission in a four-lane IM/DD system using SOA at O-band for 800G DCI. IEEE Photonics Technol. Lett., 32, 293-296(2020).

[27] Z. Qu, I. B. Djordjevic. On the probabilistic shaping and geometric shaping in optical communication systems. IEEE Access, 7, 21454-21464(2019).

[28] L. Sun et al. Dyadic probabilistic shaping of PAM-4 and PAM-8 for cost-effective VCSEL-MMF optical interconnection. IEEE Photonics J., 11, 7202611(2019).

[29] M. N. Sakib, O. Liboiron-Ladouceur. A study of error correction codes for PAM signals in data center applications. IEEE Photonics Technol. Lett., 25, 2274-2277(2013).

[30] T. Yoshida, M. Karlsson, E. Agrell. Performance metrics for systems with soft-decision FEC and probabilistic shaping. IEEE Photonics Technol. Lett., 29, 2111-2114(2017).

[31] S.-R. Moon et al. C-band PAM-4 signal transmission using soft-output MLSE and LDPC code. Opt. Express, 27, 110-120(2019).

[32] R. Gu, Z. Yang, Y. Ji. Machine learning for intelligent optical networks: a comprehensive survey. J. Network Comput. Appl., 157, 102576(2020).

[33] W. S. Saif et al. Machine learning techniques for optical performance monitoring and modulation format identification: a survey. IEEE Commun. Surv. Tutor., 22, 2839-2882(2020).

[34] V. S. Ghayal, R. Jeyachitra. Advances in Electrical and Computer Technologies(2020).

[35] S. Savian et al. Joint estimation of IQ phase and gain imbalances using convolutional neural networks on eye diagrams, STh1C.3(2018).

[36] D. Wang et al. Intelligent constellation diagram analyzer using convolutional neural network-based deep learning. Opt. Express, 25, 17150-17166(2017).

[37] S. Peng et al. Modulation classification based on signal constellation diagrams and deep learning. IEEE Trans. Neural Networks Learn. Syst., 30, 718-727(2018).

[38] K. Jiang et al. A novel digital modulation recognition algorithm based on deep convolutional neural network. Appl. Sci., 10, 1166(2020).

[39] H. Lv et al. Joint OSNR monitoring and modulation format identification on signal amplitude histograms using convolutional neural network. Opt. Fiber Technol., 61, 102455(2021).

[40] J. Du et al. A CNN-based cost-effective modulation format identification scheme by low-bandwidth direct detecting and low rate sampling for elastic optical networks. Opt. Commun., 471, 126007(2020).

[41] S. D. Dods, T. B. Anderson. Optical performance monitoring technique using delay tap asynchronous waveform sampling, OThP5(2006).

[42] D. Lippiatt et al. Impairment identification for PAM-4 transceivers and links using machine learning, W7A.5(2021).

[43] T. Tanimura et al. Convolutional neural network-based optical performance monitoring for optical transport networks. J. Opt. Commun. Networking, 11, A52-A59(2019).

[44] D. Wang et al. Modulation format recognition and OSNR estimation using CNN-based deep learning. IEEE Photonic. Technol. Lett., 29, 1667-1670(2017).

[45] Z. Zhao et al. A modulation format identification method based signal amplitude sorting and ratio calculation. Opt. Commun., 470, 125819(2020).

[46] M. C. Tan et al. Simultaneous optical performance monitoring and modulation format/bit-rate identification using principal component analysis. J. Opt. Commun. Networking, 6, 441-448(2014).

[47] X. Fan et al. Joint optical performance monitoring and modulation format/bit-rate identification by CNN-based multi-task learning. IEEE Photonics J., 10, 1-12(2018).

[48] M. Yang et al. FPGA-based real-time soft-decision LDPC performance verification for 50G-PON, W3H.2(2019).

[49] M. M. Rad et al. Passive optical network monitoring: challenges and requirements. IEEE Commun. Mag., 49, S45-S52(2011).

[50] Z. Pan, C. Yu, A. E. Willner. Optical performance monitoring for the next generation optical communication networks. Opt. Fiber Technol., 16, 20-45(2010).

[51] M. Awad, R. Khanna. Efficient Learning Machines(2015).

[52] S. Zhang et al. Learning k for KNN classification. ACM Trans. Intell. Syst. Technol., 8, 1-19(2017).

[53] C. H. Gladwin. Ethnographic Decision Tree Modeling(1989).

[54] J. H. Friedman. Greedy function approximation: a gradient boosting machine. Ann. Stat., 29, 1189-1232(2001).

[55] M. Mateen et al. Fundus image classification using VGG-19 architecture with PCA and SVD. Symmetry, 11, 1(2019).

[56] K. He et al. Deep residual learning for image recognition, 770-778(2016).

[57] A. Howard et al. Searching for MobileNetV3, 1314-1324(2019).

[58] M. Tan, Q. V. Le. EfficientNetV2: smaller models and faster training, 10096-10106(2021).

[59] P. J. Freire et al. Performance versus complexity study of neural network equalizers in coherent optical systems. J. Lightwave Technol., 39, 6085-6096(2021).

[60] H. Luo et al. Cost-effective multi-parameter optical performance monitoring using multi-task deep learning with adaptive ADTP and AAH. J. Lightwave Technol., 39, 1733-1741(2021).

[61] Z. Chen et al. GradNorm: gradient normalization for adaptive loss balancing in deep multitask networks, 794-803(2018).