首页 > 论文 > 中国激光 > 47卷 > 11期(pp:1106005--1)

基于Wasserstein生成对抗网络的智能光通信

Intelligent Optical Communication Based on Wasserstein Generative Adversarial Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

首先介绍激光链路通信的优势,然后介绍基于生成对抗网络(GAN)的端到端通信学习系统,提高了通信系统的实时性与全局优化性。针对传统GAN在训练与应用中模式坍塌和训练不稳定的问题,引入Wasserstein生成对抗网络进行改进。最后将Wasserstein生成对抗网络应用于端到端通信系统中。实验结果表明,Wasserstein生成对抗网络可以对加性高斯白噪声信道和对数正态信道进行有效模拟,且解决了传统GAN训练不稳定和模式坍塌的问题。

Abstract

This study introduces an end-to-end communication learning system based on a generative adversarial network (GAN) after discussing the advantages of laser link communication. This improves the real-time and global optimization of the communication system. Moreover, this study introduces the Wasserstein GAN to resolve mode collapse and training instability in the training and application of a traditional GAN. Finally, the Wasserstein GAN is applied to the end-to-end communication system, and the experimental results show that the Wasserstein GAN can effectively simulate an additive Gaussian white noise channel and a lognormal channel, thus avoiding the training instability and mode collapse of the traditional GAN.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TN929.12; TP18

DOI:10.3788/CJL202047.1106005

所属栏目:光纤光学与光通信

基金项目:陕西省自然科学基金;

收稿日期:2020-06-05

修改稿日期:2020-07-09

网络出版日期:2020-11-01

作者单位    点击查看

牟迪:空军工程大学信息与导航学院, 陕西 西安 710077
蒙文:空军工程大学信息与导航学院, 陕西 西安 710077
赵尚弘:空军工程大学信息与导航学院, 陕西 西安 710077
王翔:空军工程大学信息与导航学院, 陕西 西安 710077
刘文亚:空军工程大学信息与导航学院, 陕西 西安 710077

联系人作者:牟迪(122992542@qq.com)

备注:陕西省自然科学基金;

【1】Zeng Y, Zhang R. Energy-efficient UAV communication with trajectory optimization [J]. IEEE Transactions on Wireless Communications. 2017, 16(6): 3747-3760.Zeng Y, Zhang R. Energy-efficient UAV communication with trajectory optimization [J]. IEEE Transactions on Wireless Communications. 2017, 16(6): 3747-3760.

【2】Hunt B R, Iler A L, Bailey C A, et al. Synthesis of atmospheric turbulence point spread functions by sparse and redundant representations [J]. Optical Engineering. 2018, 57(2): 024101.

【3】Liu J M, Wang P P, Zhang X K, et al. Deep learning based atmospheric turbulence compensation for orbital angular momentum beam distortion and communication [J]. Optics Express. 2019, 27(12): 16671-16688.

【4】Xu M M, Bu X Z, He Z L, et al. Atmospheric turbulence interference compensation for missile-borne infrared attitude measurement [J]. Infrared Physics & Technology. 2019, 97: 69-73.

【5】Pappu C S, Carroll T L, Flores B C. Simultaneous radar-communication systems using controlled chaos-based frequency modulated waveforms [J]. IEEE Access. 2020, 8: 48361-48375.

【6】O''''Shea T. Hoydis J. An introduction to deep learning for the physical layer [J]. IEEE Transactions on Cognitive Communications and Networking. 2017, 3(4): 563-575.

【7】D?rner S, Cammerer S, Hoydis J, et al. Deep learning based communication over the air [J]. IEEE Journal of Selected Topics in Signal Processing. 2018, 12(1): 132-143.

【8】Felix A, Cammerer S, D?rner S, et al. OFDM-autoencoder for end-to-end learning of communications systems . [C]∥2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), June 25-28, 2018, Kalamata, Greece. New York: IEEE. 2018.

【9】Ye H, Li G Y. Juang B H F, et al. Channel agnostic end-to-end learning based communication systems with conditional GAN . [C]∥2018 IEEE Globecom Workshops (GC Wkshps), December 9-13, 2018, Abu Dhabi, United Arab Emirates. New York: IEEE. 2018.

【10】Arjovsky M. -01-17)[2020-06-04] . https:∥arxiv. 2017, org/abs/1701: 04862.

【11】Zou P, Zhao Y H, Hu F C, et al. Research status of machine learning based signal processing in visible light communication [J]. Laser & Optoelectronics Progress. 2020, 57(1): 010001.
邹鹏, 赵一衡, 胡昉辰, 等. 基于机器学习的可见光通信信号处理研究现状 [J]. 激光与光电子学进展. 2020, 57(1): 010001.

【12】Xiang Y, Bao C C. A pa rallel-data-free speech enhancement method using multi-objective learning cycle-consistent generative adversarial network [J]. ACM Transactions on Audio, Speech, and Language Processing. 2020, 28: 1826-1838.

【13】Fournier N, Guillin A. On the rate of convergence in Wasserstein distance of the empirical measure [J]. Probability Theory and Related Fields. 2015, 162(3/4): 707-738.

【14】Wang M H, Yuan X H, Li J, et al. Propagation of radial partially coherent beams in anisotropic non-Kolmogorov turbulence [J]. Acta Optica Sinica. 2018, 38(3): 0306003.
王铭淏, 元秀华, 李军, 等. 径向部分相干光束在各向异性非Kolmogorov湍流中的传输 [J]. 光学学报. 2018, 38(3): 0306003.

【15】Baum D S, Hansen J, Salo J, et al. An interim channel model for beyond-3G systems: extending the 3GPP spatial channel model (SCM) . [C]∥2005 IEEE 61st Vehicular Technology Conference, May 30-June 1, 2005, Stockholm, Sweden. New York: IEEE. 2005, 3132-3136.

【16】Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets . [C]∥Proceedings of the 27th International Conference on Neural Information Processing Systems, December 8-13, 2014, Montreal, Quebec, Canada. New York: Curran Associates. 2014, 2: 2672-2680.

【17】Yang Z, Chen W, Wang F, et al. Improving neural machine translation with conditional sequence generative adversarial nets [2020-06-04].https:∥arxiv.org/pdf/1703.04887.pdf.[2020-06-04]. 0.

【18】Wang L, Liu J Z, Duan D P. Simulation system of QPSK and performance analysis of BER [J]. Computer Knowledge and Technology. 2011, 7(9): 1995-1996.
王林, 刘金铸, 段德平. QPSK系统仿真及误码率性能分析 [J]. 电脑知识与技术. 2011, 7(9): 1995-1996.

【19】Duchi J C, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization [J]. Journal of Machine Learning Research. 2011, 12: 2121-2159.

【20】Jin Y C, Chen X B, Mao X R, et al. Influence of modulation degree on performances of visible light communication system [J]. Chinese Journal of Lasers. 2019, 46(5): 0506001.
靳永超, 陈雄斌, 毛旭瑞, 等. 调制度对可见光通信系统性能的影响 [J]. 中国激光. 2019, 46(5): 0506001.

【21】Wang Z H, Wu S, Liu C, et al. The regression of MNIST dataset based on convolutional neural network [M]. ∥Hassanien A E, Azar A T, Gaber T, et al. The international conference on advanced machine learning technologies and applications (AMLTA2019). Advances in intelligent systems and computing. Cham: Springer. 2019, 921: 59-68.

引用该论文

Mu Di,Meng Wen,Zhao Shanghong,Wang Xiang,Liu Wenya. Intelligent Optical Communication Based on Wasserstein Generative Adversarial Network[J]. Chinese Journal of Lasers, 2020, 47(11): 1106005

牟迪,蒙文,赵尚弘,王翔,刘文亚. 基于Wasserstein生成对抗网络的智能光通信[J]. 中国激光, 2020, 47(11): 1106005

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF