Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Differentiable Machine Learning-Based Modeling for Directly-Modulated Lasers (2309.15747v2)

Published 27 Sep 2023 in eess.SP, cs.IT, and math.IT

Abstract: End-to-end learning has become a popular method for joint transmitter and receiver optimization in optical communication systems. Such approach may require a differentiable channel model, thus hindering the optimization of links based on directly modulated lasers (DMLs). This is due to the DML behavior in the large-signal regime, for which no analytical solution is available. In this paper, this problem is addressed by developing and comparing differentiable machine learning-based surrogate models. The models are quantitatively assessed in terms of root mean square error and training/testing time. Once the models are trained, the surrogates are then tested in a numerical equalization setup, resembling a practical end-to-end scenario. Based on the numerical investigation conducted, the convolutional attention transformer is shown to outperform the other models considered.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (11)
  1. J. Huang, C. Li, R. Lu, L. Li, and Z. Cao, “Beyond the 100 Gbaud Directly Modulated Laser for Short Reach Applications,” J. Semicond., vol. 42, no. 4, p. 041306, 2021.
  2. S. Yamaoka, N.-P. P. Diamantopoulos, H. Nishi, T. Fujii, K. Takeda, T. Hiraki et al., “Uncooled 100-GBaud Directly Modulated Membrane Lasers on SiC Substrate,” J. Lightwave Technol., vol. 41, no. 11, pp. 3389–3396, 2023.
  3. W.-H. Huang, H.-M. Nguyen, C.-W. Wang, M.-C. Chan, C.-C. Wei et al., “Nonlinear Equalization Based on Artificial Neural Network in DML-Based OFDM Transmission Systems,” J. Lightwave Technol., vol. 39, no. 1, pp. 73–82, 2021.
  4. B. Karanov, M. Chagnon, V. Aref, D. Lavery, P. Bayvel, and L. Schmalen, “Concept and Experimental Demonstration of Optical IM/DD End-to-End System Optimization using a Generative Model,” in Optical Fiber Communications Conference and Exhibition (OFC), 2020, p. Th2A.48.
  5. M. Srinivasan, J. Song, A. Grabowski, K. Szczerba, H. K. Iversen et al., “End-to-End Learning for VCSEL-Based Optical Interconnects: State-of-the-Art, Challenges, and Opportunities,” J. Lightwave Technol., vol. 41, no. 11, pp. 3261–3277, 2023.
  6. N. H. Zhu, Z. Shi, Z. K. Zhang, Y. M. Zhang, C. W. Zou et al., “Directly Modulated Semiconductor Lasers,” IEEE J. Sel. Top. Quantum Electron., vol. 24, no. 1, p. 1500219, 2018.
  7. M. P. Yankov, O. Jovanovic, D. Zibar, and F. D. Ros, “Recent Advances in Constellation Optimization for Fiber-Optic Channels,” in European Conference on Optical Communication (ECOC), 2022, p. Mo3D.4.
  8. D. Wang, Z. Zhang, M. Zhang, M. Fu, J. Li et al., “The Role of Digital Twin in Optical Communication: Fault Management, Hardware Configuration, and Transmission Simulation,” IEEE Commun. Mag., vol. 59, no. 1, pp. 133–139, 2021.
  9. S. Hernandez, C. Peucheret, O. Jovanovic, F. D. Ros, and D. Zibar, “Data-Driven Modeling of Directly-Modulated Lasers,” in European Conference on Optical Communication (ECOC), 2023, p. M.A.3.3.
  10. J. Cartledge and R. Srinivasan, “Extraction of dfb laser rate equation parameters for system simulation purposes,” J. Lightwave Technol., vol. 15, no. 5, pp. 852–860, 1997.
  11. S. Li, X. Jin, Y. Xuan, X. Zhou, W. Chen et al., “Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting,” Adv. Neural Inf. Process, vol. 32, p. 471, 2019.
Citations (3)

Summary

We haven't generated a summary for this paper yet.