Abstract
To satisfy the growing throughput demand of data-intensive applications, the performance of optical communication systems increased dramatically in recent years. With higher throughput, more advanced equalizers are crucial, to compensate for impairments caused by intersymbol interference (ISI). Latest research shows that artificial neural network (ANN)-based equalizers are promising candidates to replace traditional algorithms for high-throughput communications. However, ANNs often introduce high complexity, limiting the achievable throughput of the hardware implementation. In this work, we present a high-performance field programmable gate array (FPGA) implementation of an ANN-based equalizer, which meets the throughput requirements of modern optical communication systems. Our implementation is based on a cross-layer design approach featuring optimizations from the algorithm down to the hardware architecture. Furthermore, we present a framework to reduce the latency of the ANN-based equalizer under given throughput constraints. As a result, the bit error rate (BER) of our equalizer is around one order of magnitude lower than that of a conventional one, while the corresponding FPGA implementation achieves a throughput of more than 40 GBd, outperforming a high-performance graphics processing unit (GPU) by four orders of magnitude for a similar batch size.
This work was carried out in the framework of the CELTIC-NEXT project AI-NET-ANTILLAS (C2019/3-3) and was funded by the German Federal Ministry of Education and Research (BMBF) under grant agreements 16KIS1316 and 16KIS1317 as well as under grant 16KISK004 (Open6GHuB).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amari, A., Dobre, O.A., Venkatesan, R., Kumar, O.S.S., Ciblat, P., Jaouën, Y.: A survey on fiber nonlinearity compensation for 400 Gb/s and beyond optical communication systems. IEEE Commun. Surv. Tutor. 19(4), 3097–3113 (2017). https://doi.org/10.1109/COMST.2017.2719958
Araujo, A., Norris, W.D., Sim, J.: Computing receptive fields of convolutional neural networks. Distill 4(11), e21 (2019)
Bayvel, P., et al.: Maximizing the optical network capacity. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 374(2062), 20140440 (2016)
Eriksson, T.A., Bülow, H., Leven, A.: Applying neural networks in optical communication systems: possible pitfalls. IEEE Photonics Technol. Lett. 29(23), 2091–2094 (2017). https://doi.org/10.1109/LPT.2017.2755663
Freire, P.J., et al.: Implementing neural network-based equalizers in a coherent optical transmission system using field-programmable gate arrays (2022)
Huang, X., Zhang, D., Hu, X., Ye, C., Zhang, K.: Low-complexity recurrent neural network based equalizer with embedded parallelization for 100-Gbit/s/\(\lambda \)PON. J. Lightwave Technol. 40(5), 1353–1359 (2022)
Kaneda, N., et al.: Fixed-point analysis and FPGA implementation of deep neural network based equalizers for high-speed PON. J. Lightwave Technol. 40(7), 1972–1980 (2022)
Khan, F.N., Fan, Q., Lu, C., Lau, A.P.T.: An optical communication’s perspective on machine learning and its applications. J. Lightwave Technol. 37(2), 493–516 (2019)
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. 46(19), 4980–4983 (2021)
Ney, J., et al.: Efficient FPGA implementation of an ANN-based demapper using cross-layer analysis. Electronics 11(7), 1138 (2022)
Ney, J., Lauinger, V., Schmalen, L., Wehn, N.: Unsupervised ANN-based equalizer and its trainable FPGA implementation (2023)
Nikolic, M., et al.: Bitpruning: learning bitlengths for aggressive and accurate quantization. arXiv Prepint (2020). https://arxiv.org/abs/2002.03090
Sato, Y.: A method of self-recovering equalization for multilevel amplitude-modulation systems. IEEE Trans. Commun. 23(6), 679–682 (1975)
Schaedler, M., Bluemm, C., Kuschnerov, M., Pittalá, F., Calabró, S., Pachnicke, S.: Deep neural network equalization for optical short reach communication. Appl. Sci. 9(21), 4675 (2019)
Zerguine, A., Shafi, A., Bettayeb, M.: Multilayer perceptron-based DFE with lattice structure. IEEE Trans. Neural Netw. 12(3), 532–545 (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ney, J., Füllner, C., Lauinger, V., Schmalen, L., Randel, S., Wehn, N. (2023). From Algorithm to Implementation: Enabling High-Throughput CNN-Based Equalization on FPGA for Optical Communications. In: Silvano, C., Pilato, C., Reichenbach, M. (eds) Embedded Computer Systems: Architectures, Modeling, and Simulation. SAMOS 2023. Lecture Notes in Computer Science, vol 14385. Springer, Cham. https://doi.org/10.1007/978-3-031-46077-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-46077-7_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46076-0
Online ISBN: 978-3-031-46077-7
eBook Packages: Computer ScienceComputer Science (R0)