基于人工智能技术的光通信网络应用研究

doi:10.11959/j.issn.1000-436x.2020004

通信学报 ›› 2020, Vol. 41 ›› Issue (1): 162-168.doi: 10.11959/j.issn.1000-436x.2020004

基于人工智能技术的光通信网络应用研究

沈纲祥

苏州大学苏州市先进光通信网络技术重点实验室，江苏苏州 215006

修回日期:2019-10-03 出版日期:2020-01-25 发布日期:2020-02-11
作者简介:沈纲祥（1975- ），男，浙江绍兴人，博士，苏州大学特聘教授，主要研究方向为光通信网络技术
基金资助:
国家重点研发计划基金资助项目(2018YFB1801701);国家自然科学基金资助项目(61671313);江苏省优势学科基金资助项目

Application research of optical communication network based on artificial intelligence technique

Gangxiang SHEN

Suzhou Key Laboratory of Advanced Optical Communication Network Technology,Soochow University,Suzhou 215006,China

Revised:2019-10-03 Online:2020-01-25 Published:2020-02-11
Supported by:
The National Key Research and Development Program of China(2018YFB1801701);The National Science Foundation of China(61671313);Priority Academic Program Development of Jiangsu Higher Education Institution

摘要/Abstract

摘要：

针对人工智能（AI）技术在光通信网络中的应用进行探讨。主要介绍了 AI 技术代表性应用和光通信网络开放性导致的 AI 技术失效的潜在风险，并针对这些风险提出了一些应对策略，主要包括通过单元化小型化的AI系统建模，与传统经典网络建模和规划方法相结合，提高AI技术的有效性和可解释性。同时，针对AI技术可能失效和遭受攻击提出了基于网络保护的应对策略。

关键词: 人工智能, 光通信网络, 服务水平协议, 黑盒子, 辅助性, 决策性

Abstract:

The applications of artificial intelligence (AI) technique in optical communication networks were explored.Some representative AI applications and potential risks due to the failure of the AI technique were discussed.To address these risks,methods including systematic AI modeling through unitizing and miniaturizing sub-systems and cooperation with traditional network modeling and planning methods were proposed,which were expected to help improve the effectiveness and practicality of the application of the AI technique.Finally,to recover a system from the failure of its employed AI technique or attacks,some protection strategies were proposed.

Key words: artificial intelligence, optical communication network, service level agreement, blackbox, assistive, decisive

中图分类号:

TP393

沈纲祥. 基于人工智能技术的光通信网络应用研究[J]. 通信学报, 2020, 41(1): 162-168.

Gangxiang SHEN. Application research of optical communication network based on artificial intelligence technique[J]. Journal on Communications, 2020, 41(1): 162-168.

图/表 2

参考文献 21

[1]	MATA J , MUGUEL I , DURAN R J ,et al. Artificial intelligence (AI) methods in optical networks:a comprehensive survey[J]. Optical Switching and Networking, 2018,28(4): 43-57.
[2]	MUSUMECI F , ROTTONDI C , NAG A ,et al. An overview on application of machine learning techniques in optical networks[J]. IEEE Communications Surveys ＆ Tutorials, 2019,21(2): 1383-1408.
[3]	ZHANG J , CHEN W , GAO M ,et al. Intelligent adaptive coherent optical receiver based on convolutional neural network and clustering algorithm[J]. Optics Express, 2018,26(14): 18684-18698.
[4]	THRANE J , WASS J , PIELS M ,et al. Machine learning techniques for optical performance monitoring from directly detected PDM-QAM signals[J]. IEEE/OSA Journal of Lightwave Technology, 2017,35(4): 868-875.
[5]	KHAN F N , ZHONG K,AL-ARASHI W H ,et al. Modulation format identification in coherent receivers using deep machine learning[J]. IEEE Photonics Technology Letters, 2016,28(17): 1886-1889.
[6]	ROTTONDI C , BARLETTA L , GIUSTI A ,et al. Machine-learning method for quality of transmission prediction of unestablished lightpaths[J]. IEEE/OSA Journal of Optical Communications and Networking, 2018,10(2): A286-A297.
[7]	MORAIS R M , PEDRO J . Machine learning models for estimating quality of transmission in DWDM networks[J]. IEEE/OSA Journal of Optical Communications and Networking, 2018,10(10): D84-D99.
[8]	SAMADI P , AMAR D , LEPERS C ,et al. Quality of transmission prediction with machine learning for dynamic operation of optical WDM networks[C]// 2017 European Conference on Optical Communication. IEEE/OSA, 2017: 1-3.
[9]	SHAHKARAMI S , MUSUMECI F , CUGINI F ,et al. Machine-learning-based soft-failure detection and identification in optical networks[C]// 2018 Optical Fiber Communications Conference and Exposition. IEEE/OSA, 2018: 1-3.
[10]	VELASCO L , SHARIATI B , VELA A P ,et al. Learning from the optical spectrum:soft-failure identification and localization[C]// 2018 Optical Fiber Communications Conference and Exposition. IEEE/OSA, 2018: 1-3.
[11]	PESIC J , LE ROUZIC E , BROCHIER N ,et al. Proactive restoration of optical links based on the classification of events[C]// 15th International Conference on Optical Network Design and Modeling. IEEE/OSA, 2011: 1-6.
[12]	NATALINO C , SCHIANO M , DI GIGLIO A ,et al. Field demonstra tion of machine-learning-aided detection and identification of jamming attacks in optical networks[C]// 2018 European Conference on Optical Communication. IEEE/OSA, 2018: 1-3.
[13]	LI Y , HUA N , YU Y ,et al. Light source and trail recognition via optical spectrum feature analysis for optical network security[J]. IEEE Communications Letters, 2018,22(5): 982-985.
[14]	POINTURIER Y . Design of low-margin optical networks[J]. IEEE/OSA Journal of Optical Communications and Networking, 2017,9(1): A9-A17.
[15]	CABALLERO F J V , et al . Machine learning based linear and nonlinear noise estimation[J]. IEEE/OSA Journal of Optical Communications and Networking, 2018,10(10): D42-D51.
[16]	ZHU S , GUTTERMAN C L , MO W ,et al. Machine learning based prediction of erbium-doped fiber WDM line amplifier gain spectra[C]// 2018 European Conference on Optical Communication. IEEE/OSA, 2018: 1-3.
[17]	HUANG Y ,et al. Dynamic mitigation of EDFA power excursions with machine learning[J]. Optics Express, 2017,25(3): 2245-2258.
[18]	MO W , GUTTERMAN C L , LI Y ,et al. Deep-neural-network-based wavelength selection and switching in ROADM systems[J]. IEEE/OSA Journal of Optical Communications and Networking, 2018,10(10): D1-D11.
[19]	JOHANNISSON P , AGRELL E . Modeling of nonlinear signal distortion in fiber-optic networks[J]. IEEE/OSA Journal of Lightwave Technology, 2014,32(23): 4544-4552.
[20]	WANG X , SHEN G , ZHU Z ,et al. Benefits of sub-band virtual concatenation for enhancing availability of elastic optical networks[J]. IEEE/OSA Journal of Lightwave Technology, 2016,34(4): 1098-1110.
[21]	SHEN G , GUO H , BOSE S K . Survivable elastic optical networks:survey and perspective (invited)[J]. Photonic Network Communications, 2016,31(1): 71-87.

基于人工智能技术的光通信网络应用研究

Application research of optical communication network based on artificial intelligence technique

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 2

参考文献 21

相关文章 14

Metrics

推荐阅读 0

[1]	江沸菠, 彭于波, 董莉. 面向6G的深度图像语义通信模型[J]. 通信学报, 2023, 44(3): 198-208.
[2]	王敬宇, 庄子睿. 知识定义多模态网络按需服务体系研究[J]. 通信学报, 2022, 43(4): 71-82.
[3]	牛志升, 周盛, 孙宇璇. 面向“双碳”战略的绿色通信与网络：挑战与对策[J]. 通信学报, 2022, 43(2): 1-14.
[4]	徐思雅, 邢逸斐, 郭少勇, 杨超, 邱雪松, 孟洛明. 基于深度强化学习的能源互联网智能巡检任务分配机制[J]. 通信学报, 2021, 42(5): 191-204.
[5]	刘传宏, 郭彩丽, 杨洋, 冯春燕, 孙启政, 陈九九. 人工智能物联网中面向智能任务的语义通信方法[J]. 通信学报, 2021, 42(11): 97-108.
[6]	黄韬, 刘江, 汪硕, 张晨, 刘韵洁. 未来网络技术与发展趋势综述[J]. 通信学报, 2021, 42(1): 130-150.
[7]	伏玉笋,杨根科. 人工智能在移动通信中的应用：挑战与实践[J]. 通信学报, 2020, 41(9): 190-201.
[8]	梁应敞,谭俊杰,Dusit Niyato. 智能无线通信技术研究概况[J]. 通信学报, 2020, 41(7): 1-17.
[9]	张艳硕,李文敬,陈雷,毕伟,杨涛. 基于特征值的可验证特殊门限秘密共享方案[J]. 通信学报, 2018, 39(8): 169-175.
[10]	孙鸿宇,何远,王基策,董颖,朱立鹏,王鹤,张玉清. 人工智能技术在安全漏洞领域的应用[J]. 通信学报, 2018, 39(8): 1-17.
[11]	张平,刘会永,李文璟,周凡钦. 工业智能网——工业互联网的深化与升级[J]. 通信学报, 2018, 39(12): 134-140.
[12]	魏亮,黄韬,张娇,王泽南,刘江,刘韵洁. 基于强化学习的服务链映射算法[J]. 通信学报, 2018, 39(1): 90-100.
[13]	贺倩,冯志勇,张平. 基于人工智能技术的认知无线网络重构决策算法[J]. 通信学报, 2012, 33(7): 96-102.
[14]	薛永增,李生,赵铁军,杨沐昀. 短语统计机器翻译的句法调序模型[J]. 通信学报, 2008, 29(1): 7-14.