Gain adaptive tuning method for fiber Raman amplifier based on two-stage neural networks and double weights updates

Abstract

We present a gain adaptive tuning method for fiber Raman amplifier (FRA) using two-stage neural networks (NNs) and double weights updates. After training the connection weights of two-stage NNs separately in training phase, the connection weights of the unified NN are updated again in verification phase according to error between the predicted and target gains to eliminate the inherent error of the NNs. The simulation results show that the mean of root mean square error (RMSE) and maximum error of gains are 0.131 dB and 0.281 dB, respectively. It shows that the method can realize adaptive adjustment function of FRA gain with high accuracy.

References

[1] Neto B, Teixeira A L J, Wada N, et al. Efficient use of hybrid genetic algorithms in the gain optimization of distributed Raman amplifiers[J]. Optics express, 2007, 15(26):17520-17528.

[2] Qiang L, Govind A. Vector theory of stimulated Raman scattering and its application to fiber-based Raman amplifiers[J]. Journal of the optical society of America B, 2003, 20(8):1616-1631.

[3] Mu K L, Zhao Z Z, Wang Z K, et al. Raman/EDFA hybrid bidirectional amplifier for fiber-optic time and frequency synchronization[J]. Optics express, 2021, 29(5):6365-6367.

[4] Zhang T, Zhang X P, Zhang G D. Distributed fiber Raman amplifiers with incoherent pumping[J]. IEEE photonics technology letters, 2005, 17(6):1175-1177.

[5] Ashraf A M K, Fathy M M. Raman amplifier performance under new wavelength ranges[J]. Journal of optical communications, 2016, 37(1):9-21.

[6] Chang J H, Zhang M D, Sun X H. An improved calculation method for fiber Raman amplifier equations with multi-wavelength pumping[J]. Chinese optics letters, 2004, 2(8):441-444.

[7] Liang S J, Jain S, Xu L, et al. High gain, low noise, spectral-gain-controlled broadband lumped fiber Raman amplifier[J]. Journal of lightwave technology, 2021, 39(5):1458-1463.

[8] Jake B. Raman amplification for fiber communications systems[J]. Journal of lightwave technology, 2004, 22(1):79-93.

[9] Shirley P N C, Luiz C C, Maria J P, et al. An analytical approximated solution for the gain of broadband Raman amplifiers with multiple counter-pumps[J]. Journal of lightwave technology, 2009, 27(7):944-951.

[10] Chen Y F, Du J B, Huang Y T, et al. Intelligent gain flattening in wavelength and space domain for FMF Raman amplification by machine learning based inverse design[J]. Optics express, 2020, 28(8):11911-11920.

[11] Huang Y T, Du J B, Chen Y F, et al. Machine learning assisted inverse design for ultrafine, dynamic and arbitrary gain spectrum shaping of Raman amplification[J]. Photonics, 2021, 8(7):260-270.

[12] Yang J, Zhao J. A novel parallel merge neural network with streams of spiking neural network and artificial neural network[J]. Information sciences, 2023, 642: 119034.

[13] Ortega-Fernandez I, Sestelo M, Villanueva N M. Explainable generalized additive neural networks with independent neural network training[J]. Statistics and computing, 2024, 34(1):1-11.

[14] Zhou J H, Chen J P, Li X W, et al. Robust, compact, and flexible neural model for a fiber Raman amplifier[J]. Journal of lightwave technology, 2006, 24(6):2362-2367.

[15] Yankov M, Zibar D, Carena A, et al. Forward Raman amplifier optimization using machine learning-aided physical modeling[C]. 2022 27th OptoElectronics and Communications Conference (OECC) and 2022 International Conference on Photonics in Switching and Computing (PSC), July 3–6, 2022, Toyama, Japan, 2022. New York: IEEE

[16] Yankov M, Ros F, Moura U, et al. Flexible Raman amplifier optimization based on machine learning-aided physical stimulated Raman scattering model[J]. Journal of lightwave technology, 2023, 41(2):508-514.

[17] Chen J, Jiang H. Optimal design of gain-flattened Raman fiber amplifiers using a hybrid approach combining randomized neural networks and differential evolution algorithm[J]. IEEE photonics journal, 2018, 10(2):7101915.

[18] Gong J M, Liu F, Wu Y J, et al. Design of Raman fiber amplifier based on neural network and artificial bee colony algorithm[J]. Acta optica sinica, 2021, 41(20):2006002 (in Chinese)

[19] Soltani M, Ros F D, Brusin A M R, et al. Experimental characterization of Raman amplifier optimization through inverse system design[J]. Journal of lightwave technology, 2022, 40(12):3546-3556.

[20] Darko Z, Ann M R B, Uiara C M, et al. Inverse system design using machine learning: the Raman amplifier case[J]. Journal of lightwave technology, 2020, 38(4):736-752.

[21] Uiara C M, Md A I, Morteza K, et al. Multi-band programmable gain Raman amplifer[J]. Journal of lightwave technology, 2021, 39(2):429-438.

[22] Uiara C M, Ann M R B, Andrea C, et al. Simultaneous gain profile design and noise figure prediction for Raman amplifiers using machine learning[J]. Optics letters, 2021, 46(5):1157-1160.

[23] Mohammed N I. Raman amplifiers for telecommunications[J]. IEEE journal of selected topics in quantum electronics, 2002, 8(3):548-559.