Demonstration of a low-complexity memory-polynomial-aided neural network equalizer for CAP visible-light communication with superluminescent diode

Fangchen Hu; Jorge A. Holguin-Lerma; Yuan Mao; Peng Zou; Chao Shen; Tien Khee Ng; Boon S. Ooi; Nan Chi

doi:10.29026/oea.2020.200009

Article navigation > Opto-Electronic Advances > 2020 Vol. 3 > No. 8 > 200009

Next Article Previous Article

Hu F C, Holguin-Lerma J A, Mao Y, Zou P, Shen C et al. Demonstration of a low-complexity memory-polynomial-aided neural network equalizer for CAP visible-light communication with superluminescent diode. Opto-Electron Adv 3, 200009 (2020). doi: 10.29026/oea.2020.200009

Citation:

Hu F C, Holguin-Lerma J A, Mao Y, Zou P, Shen C et al. Demonstration of a low-complexity memory-polynomial-aided neural network equalizer for CAP visible-light communication with superluminescent diode. Opto-Electron Adv 3, 200009 (2020). doi: 10.29026/oea.2020.200009

Original Article Open Access

Demonstration of a low-complexity memory-polynomial-aided neural network equalizer for CAP visible-light communication with superluminescent diode

1.
Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai 200433, China
2.
Photonics Labora-tory, King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Saudi Arabia

More Information

^*Corresponding authors: B S Ooi, E-mail: Boon.Ooi@kaust.edu.sa; N Chi, E-mail: nanchi@fudan.edu.cn

Received Date 06 April 2020

Accepted Date 17 May 2020

Available Online 21 August 2020

Published Date 21 August 2020

Abstract

Abstract

Visible-light communication (VLC) stands as a promising component of the future communication network by providing high-capacity, low-latency, and high-security wireless communication. Superluminescent diode (SLD) is proposed as a new light emitter in the VLC system due to its properties of droop-free emission, high optical power density, and low speckle-noise. In this paper, we analyze a VLC system based on SLD, demonstrating effective implementation of carrierless amplitude and phase modulation (CAP). We create a low-complexity memory-polynomial-aided neural network (MPANN) to replace the traditional finite impulse response (FIR) post-equalization filters of CAP, leading to significant mitigation of the linear and nonlinear distortion of the VLC channel. The MPANN shows a gain in Q factor of up to 2.7 dB higher than other equalizers, and more than four times lower complexity than a standard deep neural network (DNN), hence, the proposed MPANN opens a pathway for the next generation of robust and efficient neural network equalizers in VLC. We experimentally demonstrate a proof-of-concept 2.95-Gbit/s transmission using MPANN-aided CAP with 16-quadrature amplitude modulation (16-QAM) through a 30-cm channel based on the 442-nm blue SLD emitter.
- superluminescent diode /
- visible-light communication /
- neural network

FullText(HTML)

References

[1]	Tanaka Y, Haruyama S, Nakagawa M. Wireless optical transmissions with white colored LED for wireless home links. In 11th IEEE International Symposium on Personal Indoor and Mobile Radio Communications 1325-1329 (IEEE, 2000); http://doi.org/10.1109/PIMRC.2000.881634. Google Scholar
[2]	Chi N, Haas H, Kavehrad M, Little T D C, Huang X L. Visible light communications: demand factors, benefits and opportunities[Guest Editorial]. IEEE Wirel Commun 22, 5-7 (2015). Google Scholar
[3]	Haas H. LiFi is a paradigm-shifting 5G technology. Rev Phys 3, 26-31 (2018). doi: 10.1016/j.revip.2017.10.001 CrossRef Google Scholar
[4]	Russell C L. 5 G wireless telecommunications expansion: Public health and environmental implications. Environ Res 165, 484-495 (2018). doi: 10.1016/j.envres.2018.01.016 CrossRef Google Scholar
[5]	Zhang Y L, Wang L, Wang K, Wong K S, Wu K S. Recent advances in the hardware of visible light communication. IEEE Access 7, 91093-91104 (2019). doi: 10.1109/ACCESS.2019.2927054 CrossRef Google Scholar
[6]	Stepniak G, Kowalczyk M, Maksymiuk L, Siuzdak J. Transmission beyond 100 Mbit/s using LED both as a transmitter and receiver. IEEE Photon Technol Lett 27, 2067-2070 (2015). doi: 10.1109/LPT.2015.2451006 CrossRef Google Scholar
[7]	Ho K T, Chen R, Liu G Y, Shen C, Holguin-Lerma J et al. 3.2 Gigabit-per-second visible light communication link with InGaN/GaN MQW micro-photodetector. Opt Express 26, 3037-3045 (2018). doi: 10.1364/OE.26.003037 CrossRef Google Scholar
[8]	Kang C H, Liu G Y, Lee C, Alkhazragi O, Wagstaff J M et al. Semipolar (2021) InGaN/GaN micro-photodetector for gigabit-per-second visible light communication. Appl Phys Express 13, 014001 (2020). doi: 10.7567/1882-0786/ab58eb CrossRef Google Scholar
[9]	Cheng C H, Shen C C, Kao H Y, Hsieh D H, Wang H Y et al. 850/940-nm VCSEL for optical communication and 3D sensing. Opto-Electron Adv 1, 180005 (2018). Google Scholar
[10]	Tsonev D, Chun H, Rajbhandari S, McKendry J J D, Videv S et al. A 3-Gb/s single-LED OFDM-based wireless VLC link using a gallium nitride μ LED. IEEE Photon Technol Lett 26, 637-640 (2014). doi: 10.1109/LPT.2013.2297621 CrossRef Google Scholar
[11]	Janjua B, Oubei H M, Durán Retamal J R, Ng T K, Tsai C T et al. Going beyond 4 Gbps data rate by employing RGB laser diodes for visible light communication. Opt Express 23, 18746-18753 (2015). doi: 10.1364/OE.23.018746 CrossRef Google Scholar
[12]	Bian R, Tavakkolnia I, Haas H. 15.73 Gb/s visible light communication with off-the-shelf LEDs. J Light Technol 37, 2418-2424 (2019). doi: 10.1109/JLT.2019.2906464 CrossRef Google Scholar
[13]	Shi J Y, Zhu X, Wang F M, Zou P, Zhou Y J et al. Net data rate of 14.6 Gbit/s underwater VLC utilizing silicon substrate common-anode five primary colors LED. In Optical Fiber Communication Conference (OFC) M3I.5 (OSA, 2019); http://doi.org/10.1364/OFC.2019.M3I.5. Google Scholar
[14]	Wei L Y, Chow C W, Liu Y, Yeh C H. Multi-Gbit/s phosphor-based white-light and blue-filter-free visible light communication and lighting system with practical transmission distance. Opt Express 28, 7375-7381 (2020). Google Scholar
[15]	Feltin E, Castiglia A, Cosendey G, Sulmoni L, Carlin J F et al. Broadband blue superluminescent light-emitting diodes based on GaN. Appl Phys Lett 95, 081107 (2009). doi: 10.1063/1.3202786 CrossRef Google Scholar
[16]	Kafar A, Stańczyk S, Wiśniewski P, Oto T, Makarowa I et al. Design and optimization of InGaN superluminescent diodes. Phys Status Solidi 212, 997-1004 (2015). doi: 10.1002/pssa.201431741 CrossRef Google Scholar
[17]	Shen C, Ng T K, Leonard J T, Pourhashemi A, Nakamura S et al. High-brightness semipolar (2021) blue InGaN/GaN superluminescent diodes for droop-free solid-state lighting and visible-light communications. Opt Lett 41, 2608-2611 (2016). doi: 10.1364/OL.41.002608 CrossRef Google Scholar
[18]	Cahill R, Maaskant P P, Akhter M, Corbett B. High power surface emitting InGaN superluminescent light-emitting diodes. Appl Phys Lett 115, 171102 (2019). doi: 10.1063/1.5118953 CrossRef Google Scholar
[19]	Rashidi A, Rishinaramangalam A K, Aragon A A, Mishkat-Ul-Masabih S, Monavarian M et al. High-speed nonpolar InGaN/GaN superluminescent diode with 2.5 GHz modulation bandwidth. IEEE Photon Technol Lett 32, 383-386 (2020). doi: 10.1109/LPT.2020.2976060 CrossRef Google Scholar
[20]	Andreeva E V, Anikeev, A S, Il'chenko, S N, Chamorovskiy, A, Shidlovski, V R et al. Highly efficient superluminescent diodes and SLD-based combined light sources of red spectral range for applications in biomedical imaging. In Proceedings of the SPIE 10483, Optical Coherence Tomography and Coherence Domain Optical Methods in Biomedicine XXⅡ, 104832T (SPIE, 2018); http://doi.org/10.1117/12.2288246. Google Scholar
[21]	Goldberg G R, Boldin A, Andersson S M L, Ivanov P, Ozaki N et al. Gallium nitride superluminescent light emitting diodes for optical coherence tomography applications. IEEE J Sel Top Quantum Electron 23, 2000511 (2017). Google Scholar
[22]	Primerov N, Dahdah J, Gloor S, von Niederhäusern T, Matuschek N et al. A compact red-green-blue superluminescent diode module: A novel light source for AR microdisplays. in Proceedings of the SPIE Digital Optical Technologies 2019 110620F (SPIE, 2019); http://doi.org/10.1117/12.2527626. Google Scholar
[23]	Alatawi A A, Holguin-Lerma J A, Kang C H, Shen C, Subedi R C et al. High-power blue superluminescent diode for high CRI lighting and high-speed visible light communication. Opt Express 26, 26355-26364 (2018). doi: 10.1364/OE.26.026355 CrossRef Google Scholar
[24]	Shen C, Lee C, Ng T K, Nakamura S, Speck J S et al. High-speed 405-nm superluminescent diode (SLD) with 807-MHz modulation bandwidth. Opt Express 24, 20281-20286 (2016). doi: 10.1364/OE.24.020281 CrossRef Google Scholar
[25]	Shen C, Holguin-Lerma J A, Alatawi A A, Zou P, Chi N et al. Group-Ⅲ-nitride superluminescent diodes for solid-state lighting and high-speed visible light communications. IEEE J Sel Top Quantum Electron 25, 2000110 (2019). Google Scholar
[26]	Hu F C, Holguin-Lerma J A, Mao Y, Shen C, Sun X B et al. 3.8-Gbit/s visible light communication (VLC) based on 443-nm superluminescent diode and bit-loading discrete-multiple-tone (DMT) modulation scheme. In Proceedings of the SPIE 11307, Broadband Access Communication Technologies XIV 113070H (SPIE, 2020); http://doi.org/10.1117/12.2543983. Google Scholar
[27]	Chi N, Shi M. Advanced modulation formats for underwater visible light communications[Invited]. Chin Opt Lett 16, 120603 (2018). doi: 10.3788/COL201816.120603 CrossRef Google Scholar
[28]	Wu F M, Lin C T, Wei C C, Chen C W, Chen Z Y et al. Performance comparison of OFDM signal and CAP signal over high capacity RGB-LED-based WDM visible light communication. IEEE Photonics J 5, 7901507 (2013). Google Scholar
[29]	Li G Q, Hu F C, Zhao Y H, Chi N. Enhanced performance of a phosphorescent white LED CAP 64QAM VLC system utilizing deep neural network (DNN) post equalization. In 2019 IEEE/CIC International Conference on Communications in China (ICCC) 173-176 (IEEE, 2019); http://doi.org/10.1109/ICCChina.2019.8855926. Google Scholar
[30]	Rodes R, Wieckowski M, Pham T T, Jensen J B, Turkiewicz J et al. Carrierless amplitude phase modulation of VCSEL with 4 bit/s/Hz spectral efficiency for use in WDM-PON. Opt Express 19, 26551-26556 (2011). Google Scholar
[31]	Osahon I N, Rajbhandari S, Popoola W O. Performance comparison of equalization techniques for SI-POF multi-Gigabit communication with PAM- M and device non-linearities. J Light Technol 36, 2301-2308 (2018). doi: 10.1109/JLT.2018.2811045 CrossRef Google Scholar
[32]	Feng J L, Lu S N. Performance analysis of various activation functions in artificial neural networks. J Phys: Conf Ser 1237, 022030 (2019). doi: 10.1088/1742-6596/1237/2/022030 CrossRef Google Scholar
[33]	Zhang J. Memory-polynomial digital pre-distortion for linearity improvement of directly-modulated multi-IF-over-Fiber LTE mobile fronthaul. In Optical Fiber Communications Conference (OFC), Tu2B.3 (OSA, 2016). Google Scholar
[34]	Morgan D R, Ma Z, Kim J, Zierdt M G, Pastalan J. A generalized memory polynomial model for digital predistortion of RF power amplifiers. IEEE Trans Signal Process 54, 3852-3860 (2006). doi: 10.1109/TSP.2006.879264 CrossRef Google Scholar
[35]	Ramachandran P, Zoph B, Le Q V. Searching for activation functions. arXiv: 1710.05941 (2017). Google Scholar
[36]	Shu L, Li J Q, Wan Z Q, Zhang W J, Fu S N et al. Overestimation trap of artificial neural network: Learning the rule of PRBS. In 2018 European Conference on Optical Communication (ECOC) 1-3 (IEEE, 2018); http://doi.org/10.1109/ECOC.2018.8535327. Google Scholar
[37]	Lu X Y, Lu C, Yu W X, Qiao L, Liang S Y et al. Memory-controlled deep LSTM neural network post-equalizer used in high-speed PAM VLC system. Opt Express 27, 7822-7833 (2019). doi: 10.1364/OE.27.007822 CrossRef Google Scholar
[38]	Li M, Zhang T, Chen Y Q, Smola A J. Efficient mini-batch training for stochastic optimization. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 661-670 (ACM Press, 2014); http://doi.org/10.1145/2623330.2623612. Google Scholar
[39]	Chi N, Zhou Y J, Liang S Y, Wang F M, Li J H et al. Enabling technologies for high-Speed visible Light communication employing CAP modulation. J Light Technol 36, 510-518 (2018). doi: 10.1109/JLT.2017.2783906 CrossRef Google Scholar
[40]	Wang Y G, Tao L, Huang X X, Shi J Y, Chi N. 8-Gb/s RGBY LED-based WDM VLC system employing high-order CAP modulation and hybrid post equalizer. IEEE Photon J 7, 7904507 (2015). Google Scholar
[41]	Haigh P A, Chvojka P, Zvánovec S, Ghassemlooy Z, Darwazeh I. Analysis of Nyquist pulse shapes for carrierless amplitude and phase modulation in visible light communications. J Light Technol 36, 5023-5029 (2018). Google Scholar
[42]	Shi J Y, Zhou Y J, Zhang J W, Chi N, Yu J J. Enhanced performance utilizing joint processing algorithm for CAP signals. J Light Technol 36, 3169-3175 (2018). doi: 10.1109/JLT.2018.2834721 CrossRef Google Scholar
[43]	Chi N, Zhao Y H, Shi M, Zou P, Lu X Y. Gaussian kernel-aided deep neural network equalizer utilized in underwater PAM8 visible light communication system. Opt Express 26, 26700-26712 (2018). doi: 10.1364/OE.26.026700 CrossRef Google Scholar
[44]	Mathews V J. Adaptive polynomial filters. IEEE Signal Process Mag 8, 10-26 (1991). doi: 10.1109/79.127998 CrossRef Google Scholar
[45]	Fehenberger T, Hanik N. Mutual information as a figure of merit for optical fiber systems. arXiv: 1405.2029 (2014). Google Scholar