Journals / AURUM Mühendislik Sistemleri ve Mimarlık Dergisi / 2026 / Cilt: 10 Sayı: 1

ANALYSIS OF ERBIUM-DOPED FIBER AMPLIFIERS USED IN RING BACKBONE OPTICAL NETWORKS USING MACHINE LEARNING

HALKA OMURGALI OPTİK AĞLARDA KULLANILAN ERBİYUM KATKILI FİBER KUVVETLENDİRİCİLERİN MAKİNE ÖĞRENMESİ İLE ANALİZİ

Neda Naderi(YILDIZ TECHNICAL UNIVERSITY)0009-0002-6922-8057
N. Ozlem Unverdi(YILDIZ TECHNICAL UNIVERSITY)0000-0002-3995-3410
Pages
89–103
Publication Date
2026-06-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

These findings show that machine learning can serve as an efficient and interpretable decision support layer for impairment-aware EDFA placement without replacing full physical layer simulation.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study investigates erbium-doped fiber amplifier placement in wavelength-division multiplexing ring backbone optical networks and evaluates whether machine-learning-guided screened search can improve feasibility-aware planning.
📊
Key Findings & Data:Ring-8 to Ring-16 topologies were simulated under standard and heterogeneous scenarios using a physical layer model that includes received power, amplified spontaneous emission (ASE), nonlinear interference, and an enhanced Gaussian noise (EGN) inspired correction.
💡
Conclusion & Impact:These findings show that machine learning can serve as an efficient and interpretable decision support layer for impairment-aware EDFA placement without replacing full physical layer simulation.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:İletişim teknolojileri · halka omurgalı optik ağ · dalga boyu bölmeli çoğullama

Abstract

This study investigates erbium-doped fiber amplifier placement in wavelength-division multiplexing ring backbone optical networks and evaluates whether machine-learning-guided screened search can improve feasibility-aware planning. Ring-8 to Ring-16 topologies were simulated under standard and heterogeneous scenarios using a physical layer model that includes received power, amplified spontaneous emission (ASE), nonlinear interference, and an enhanced Gaussian noise (EGN) inspired correction. Candidate amplifier masks were ranked with a no-leak screening model and refined through bounded local search. Random Forest delivered the best screening performance, reaching receiver operating characteristic area under the curve (ROC-AUC) values of 0.9971 in the standard dataset and 0.9379 in the harder dataset, while leave-one-topology-out validation showed robust generalization across unseen ring sizes. In scaling experiments, the improved screened strategy matched the exhaustive optimum feasible ratio through Ring-16 and became 7.44 times faster than exhaustive search at Ring-16. These findings show that machine learning can serve as an efficient and interpretable decision support layer for impairment-aware EDFA placement without replacing full physical layer simulation.

Özet

Bu çalışmada, dalga boyu bölmeli çoğullamanın (Wavelength-Division Multiplexing, WDM) kullanıldığı halka omurgalı optik ağlarda erbiyum katkılı fiber kuvvetlendiricilerin (Erbium-Doped Fiber Amplifier, EDFA) yerleşimi incelenmiş ve makine öğrenmesi destekli tarama yaklaşımının uygulanabilirlik odaklı ağ planlamasına katkısı değerlendirilmiştir. Ring-8 ile Ring-16 arasındaki topolojiler, alınan güç, kuvvetlendirilmiş kendiliğinden yayılım (Amplified Spontaneous Emission, ASE), doğrusal olmayan girişim ve geliştirilmiş Gaussian gürültü (Enhanced Gaussian Noise, EGN) yaklaşımından yararlanılan düzeltmeyi içeren fiziksel katman modeli kullanılarak standart ve heterojen senaryolar altında çalışılmıştır. Aday kuvvetlendirici yerleşimleri, bilgi sızıntısı içermeyen bir tarama modeliyle sıralanmış ve ardından sınırlandırılmış yerel arama ile iyileştirilmiştir. Analizde, Rastgele Orman (Random Forest), standart veri kümesinde 0,9971 ROC-AUC (Receiver Operating Characteristic Area under the Curve, Alıcı Çalışma Karakteristiği Eğrisi Altındaki Alan) ve zorlu veri kümesinde 0,9379 ROC-AUC değeriyle en başarılı tarama performansını göstermiştir. Ayrıca bir topolojiyi dışarıda bırakarak yapılan doğrulama (leave-one-topology-out), modelin görülmemiş halka boyutları için de anlamlı biçimde genelleştirilebileceğini göstermiştir. Ölçekleme deneylerinde iyileştirilmiş taramalı strateji, Ring-16’ya kadar tam arama ile aynı uygulanabilirlik oranını sağlamış ve Ring-16’da tam aramadan 7,44 kat daha hızlı çalışmıştır. Elde edilen bulgular ile makine öğrenmesinin tam fiziksel katman benzetiminin yerini almadan, EDFA yerleşimi için verimli ve yorumlanabilir bir karar destek katmanı sunabileceği belirlenmiştir.

🔖

Cite This Article

Naderi, N., Unverdi, N. O. (2026). ANALYSIS OF ERBIUM-DOPED FIBER AMPLIFIERS USED IN RING BACKBONE OPTICAL NETWORKS USING MACHINE LEARNING. AURUM Mühendislik Sistemleri ve Mimarlık Dergisi, Cilt: 10 Sayı: 1, 89–103. https://doi.org/10.53600/ajesa.1957573

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (15)

  1. Agrawal, G. P. (2010). Fiber-optic communication systems (4th ed.). Hoboken, NJ: Wiley.
  2. Ayassi, R., Triki, A., Crespi, N., Minerva, R., & Laye, M. (2022). Survey on the use of machine learning for quality of transmission estimation in optical transport networks. Journal of Lightwave Technology, 40(17), 5803-5815. https://doi.org/10.1109/JLT.2022.3184178
  3. Azzimonti, D., Rottondi, C., Giusti, A., Tornatore, M., & Bianco, A. (2021). Comparison of domain adaptation and active learning techniques for quality of transmission estimation with small-sized training datasets. Journal of Optical Communications and Networking, 13(1), A56-A66. https://doi.org/10.1364/JOCN.401918
  4. Azodolmolky, S., Klinkowski, M., Marin-Tordera, E., Careglio, D., Sole-Pareta, J., & Tomkos, I. (2009). A survey on physical layer impairments aware routing and wavelength assignment algorithms in optical networks. Computer Networks, 53(7), 926-944. https://doi.org/10.1016/j.comnet.2008.11.014
  5. Curri, V. (2022). GNPy model of the physical layer for open and disaggregated optical networking [Invited]. Journal of Optical Communications and Networking, 14(6), C92-C104. https://doi.org/10.1364/JOCN.452868
  6. Ferrari, A., Filer, M., Balasubramanian, K., Yin, Y., Le Rouzic, E., Kundrat, J., Grammel, G., Galimberti, G., & Curri, V. (2020). GNPy: An open source application for physical layer aware open optical networks. Journal of Optical Communications and Networking, 12(6), C31-C40. https://doi.org/10.1364/JOCN.382906
  7. Ibrahimi, M., Ayoub, O., Musumeci, F., Karandin, O., Castoldi, A., Pastorelli, R., & Tornatore, M. (2020). Minimum-cost optical amplifier placement in metro networks. Journal of Lightwave Technology, 38(12), 3221-3228. https://doi.org/10.1109/JLT.2020.2991374
  8. Maryam, H., Savva, G., Panayiotou, T., Tomkos, I., & Ellinas, G. (2022). Learning quantile QoT models to address uncertainty over unseen lightpaths. Computer Networks, 212, 108992. https://doi.org/10.1016/j.comnet.2022.108992
  9. Musumeci, F., Rottondi, C., Nag, A., Macaluso, I., Zibar, D., Ruffini, M., & Tornatore, M. (2019). An overview on application of machine learning techniques in optical networks. IEEE Communications Surveys & Tutorials, 21(2), 1383-1408. https://doi.org/10.1109/COMST.2018.2880039
  10. Pedro, J., & Costa, N. (2018). Optimized hybrid Raman/EDFA amplifier placement for DWDM mesh networks. Journal of Lightwave Technology, 36(9), 1552-1561. https://doi.org/10.1109/JLT.2017.2783678
  11. Pointurier, Y. (2021). Machine learning techniques for quality of transmission estimation in optical networks. Journal of Optical Communications and Networking, 13(4), B60-B71. https://doi.org/10.1364/JOCN.417434
  12. Ramamurthy, B., Iness, J., & Mukherjee, B. (1998). Optimizing amplifier placements in a multiwavelength optical LAN/MAN: The equally powered-wavelengths case. Journal of Lightwave Technology, 16(9), 1560-1569. https://doi.org/10.1109/50.712237
  13. Ramaswami, R., Sivarajan, K. N., & Sasaki, G. H. (2009). Optical networks: A practical perspective (3rd ed.). Morgan Kaufmann.
  14. Rottondi, C., Barletta, L., Giusti, A., & Tornatore, M. (2018). Machine-learning method for quality of transmission prediction of unestablished lightpaths. Journal of Optical Communications and Networking, 10(2), A286-A297. https://doi.org/10.1364/JOCN.10.00A286
  15. Seve, E., Pesic, J., Delezoide, C., Bigo, S., & Pointurier, Y. (2018). Learning process for reducing uncertainties on network parameters and design margins. Journal of Optical Communications and Networking, 10(2), A298-A306. https://doi.org/10.1364/JOCN.10.00A298