Leveraging machine learning for space division multiplexing performance: a classifier-focused evaluation
-
Hardeep Kaur
and
Gurpreet Kaur
Abstract
This paper explores space division multiplexing as a next-generation solution for optical fiber communication systems. The purpose of this paper is to investigate how well machine learning algorithms predict the performance of SDM systems. Using simulations of SDM systems, the study evaluates classifiers such as multilayer perceptron, random forest classifier, logistic regression, naive Bayes, decision tree, and k-nearest neighbors. The performance of the classifiers is measured in terms of accuracy, cross-validation scores, and ROC (area under the curve) (AUC). The findings from dataset 1 show that MLP and KNN reach the maximum accuracy of 93. Though logistic regression has the best cross-validation score of 87, MLP is still chosen due to its superior ROC score of 99. In dataset 2, MLP achieves the maximum accuracy of 84. MLP is favoured because of its higher cross-validation score of 79 obtained using logistic regression, compared to its superior ROC score of 92. Although logistic regression exhibits good cross-validation performance, the study prefers MLP because of its superior accuracy and remarkable ROC-AUC scores in both datasets, indicating its robust classification abilities across a wide range of data distributions.
Acknowledgments
We wish to thank the APON Lab of Punjabi University, Patiala, for providing the computational system for the training and testing of the AI models of this work.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Conflict of interest: The authors state no conflict of interest.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Research funding: None declared.
-
Data availability: The raw data can be obtained on request from the corresponding author.
References
1. Agrawal, GP. Fiber-Optic Communication Systems. Hoboken, New Jersey, USA: John Wiley Sons, Inc.; 2010, 6:1–23 pp.10.1002/9780470918524Search in Google Scholar
2. Ferreira, MFS. Nonlinear Effects in Optical Fibers. Hoboken, New Jersey, USA: John Wiley Sons, Inc.; 2011, 4:1–7 pp.Search in Google Scholar
3. Trindade, S, Da Fonseca, NLS. Machine learning for spectrum defragmentation in space-division multiplexing elastic optical networks. IEEE Netw 2021;35:326–32. https://doi.org/10.1109/mnet.011.2000367.Search in Google Scholar
4. Trichili, A, Park, KH, Zghal, M, Ooi, BS, Alouini, MS. Communicating using spatial mode multiplexing : potentials , challenges and perspectives. IEEE Commun 2019;6:1–30. https://doi.org/10.1109/comst.2019.2915981.Search in Google Scholar
5. Winzer, PJ, Foschini, GJ. MIMO capacities and outage probabilities in spatially multiplexed optical transport systems. Opt Express 2011;19:16680. https://doi.org/10.1364/oe.19.016680.Search in Google Scholar PubMed
6. Yao, Q, Yang, H, Zhu, R, Yu, A, Bai, W, Tan, Y, et al.. Core, mode, and spectrum assignment based on machine learning in space division multiplexing elastic optical networks. IEEE Access 2018;6:15898–907. https://doi.org/10.1109/access.2018.2811724.Search in Google Scholar
7. Essiambre, RJ, Tkach, RW. Capacity trends and limits of optical communication networks. Proc IEEE 2012;100:1035–55. https://doi.org/10.1109/jproc.2012.2182970.Search in Google Scholar
8. Musumeci, F, Rottondi, C, Nag, A, Macaluso, I, Zibar, D, Ruffini, M, et al.. An overview on application of machine learning techniques in optical networks. IEEE Commun 2019;21:1383–408. https://doi.org/10.1109/comst.2018.2880039.Search in Google Scholar
9. Dongare, AD, Kharde, RR, Kachare, AD. Introduction to artificial neural network (ANN) methods. Int J Eng Innov Technol 2012;2:189–94.Search in Google Scholar
10. Khan, FN, Fan, Q, Lu, C, Lau, APT. An optical communication’s perspective on machine learning and its applications. J Light Technol 2019;37:493–516. https://doi.org/10.1109/jlt.2019.2897313.Search in Google Scholar
11. Mori, T, Sakamoto, T, Wada, M, Yamamoto, T, Nakajima, K. Few-mode fiber technology for mode division multiplexing. Opt Fiber Technol 2017;35:37–45. https://doi.org/10.1016/j.yofte.2016.07.011.Search in Google Scholar
12. Jiang, S, Ma, L, Zhang, Z, Xu, X, Wang, S, Du, J, et al.. Design and characterization of ring-assisted few-mode fibers for weakly coupled mode-division multiplexing transmission. J Light Technol 2018;36:5547–55. https://doi.org/10.1109/jlt.2018.2874526.Search in Google Scholar
13. Teng, Y, Natalino, C, Li, H, Yang, R, Majeed, J, Shen, S, et al.. Deep-reinforcement-learning-based RMSCA for space division multiplexing networks with multi-core fibers. J Opt Commun Netw 2024;16:C76–87. https://doi.org/10.1364/jocn.518685.Search in Google Scholar
14. Mizuno, T, Takara, H, Sano, A, Miyamoto, Y. Dense space-division multiplexed transmission systems using multi-core and multi-mode fiber. J Light Technol 2016;34:582–92. https://doi.org/10.1109/jlt.2015.2482901.Search in Google Scholar
15. Weng, Y, He, X, Pan, Z. Space division multiplexing optical communication using few-mode fibers. Opt Fiber Technol 2017;36:155–80. https://doi.org/10.1016/j.yofte.2017.03.009.Search in Google Scholar
16. Yoshikane, N, Tsuritani, T. Recent progress in space-division multiplexing optical network technology. In: 2020 24th Int. Conf. Opt. Netw. Des. Model. ONDM. 2020:10–13 pp.10.23919/ONDM48393.2020.9133031Search in Google Scholar
17. Winzer, PJ, Neilson, DT. From scaling disparities to integrated parallelism: a decathlon for a decade. J Light Technol 2017;35:1099–115. https://doi.org/10.1109/jlt.2017.2662082.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
