基于集成学习的广域光骨干网多信道传输质量预测方法

doi:10.11959/j.issn.1000-436x.2020201

通信学报 ›› 2020, Vol. 41 ›› Issue (9): 1-7.doi: 10.11959/j.issn.1000-436x.2020201

• 专题：面向智慧应急的通信与计算融合 • 下一篇

基于集成学习的广域光骨干网多信道传输质量预测方法

孙晓川^1,²,李志刚²,张明辉³,桂冠¹()

¹ 南京邮电大学通信与信息工程学院，江苏南京 210003
² 华北理工大学人工智能学院，河北唐山 063210
³ 河北工业大学电子信息工程学院，天津 300401

修回日期:2020-08-19 出版日期:2020-09-25 发布日期:2020-10-12
作者简介:孙晓川（1983- ），男，山东烟台人，博士，华北理工大学副教授，主要研究方向为未来通信网络关键技术、机器学习、群体智能|李志刚（1966- ），男，河北唐山人，博士，华北理工大学副教授，主要研究方向为网络控制理论、深度学习、数据挖掘技术|张明辉（1994- ），女，河北承德人，河北工业大学博士生，主要研究方向为机器学习、计算智能与无线网络|桂冠（1982- ），男，安徽枞阳人，博士，南京邮电大学教授，主要研究方向为基于深度学习的物理层无线通信技术
基金资助:
河北省自然科学基金资助项目(F201820918);河北省高等学校科学技术研究基金资助项目(QN2018115);国家科技部科技重大基金资助项目(2017YFE0135700);唐山市科技计划基金资助项目(19150230E)

Multi-channel QoT prediction method in wide-area optical backbone network based on ensemble learning

Xiaochuan SUN^1,²,Zhigang LI²,Minghui ZHANG³,Guan GUI¹()

¹ College of Telecommunications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
² College of Artificial Intelligence,North China University of Science and Technology,Tangshan 063210,China
³ School of Electronics and Information Engineering,Hebei University of Technology,Tianjin 300401,China

Revised:2020-08-19 Online:2020-09-25 Published:2020-10-12
Supported by:
The Natural Science Foundation of Hebei Province(F201820918);The Hebei Colleges and Universities Science Foundation(QN2018115);The S＆T Major Project of the Science and Technology Ministry of China(2017YFE0135700);The Office of Science and Technology of Tangshan(19150230E)

摘要/Abstract

摘要：

针对动态广域光骨干网中光信道传输质量预测方法精确度不足的问题，以集成学习理论为基础提出一种光信道传输质量预测方法。首先，在堆栈集成学习框架下构建了由5个多层感知器模型组成的基学习器，通过并行组合的方式实现了样本数据的同态集成学习。然后，融合基学习器的预测结果形成新的训练集，用于训练由单一多层感知器组成的元学习器。仿真结果表明，对比深度神经网络，所提方法在单信道和多信道QoT预测场景下具有更优秀的非线性逼近性能，预测精度分别提高了1.93%和3.82%。

关键词: 光骨干网, 多信道, 传输质量预测, 集成学习

Abstract:

Due to the fact that in dynamic wide-area optical backbone network the accuracies of the existing prediction methods were insufficient,a novel prediction method on quality of transmission (QoT) of optical channel was proposed based on ensemble learning theory.Firstly,under the framework of stacked ensemble learning,a base-learner including five multilayer perceptron (MLP) model was built,which could achieve homomorphic ensemble learning of sample data through parallel combination.Subsequently,the new training set fused from the predicted results of the preceding base-learner was used to training the meta-learner composed of a single MLP.The simulation results show that compared with the used deep neural network,the proposed method can obtain a more excellent nonlinear approximation in the scenarios of the single-channel and multi-channels,and the prediction accuracies have the improvements of 1.93% and 3.82% respectively.

Key words: optical backbone network, multi-channel, QoT prediction, ensemble learning

中图分类号:

TN91

孙晓川,李志刚,张明辉,桂冠. 基于集成学习的广域光骨干网多信道传输质量预测方法[J]. 通信学报, 2020, 41(9): 1-7.

Xiaochuan SUN,Zhigang LI,Minghui ZHANG,Guan GUI. Multi-channel QoT prediction method in wide-area optical backbone network based on ensemble learning[J]. Journal on Communications, 2020, 41(9): 1-7.

图/表 8

图1

表1

图2

图3

表2

图4

表3

图5

参考文献 18

[1]	张平, 陶运铮, 张治 . 5G 若干关键技术评述[J]. 通信学报, 2016,37(7): 15-29.
	ZHANG P , TAO Y Z , ZHANG Z . Survey of several key technologies for 5G[J]. Journal on Communications, 2016,37(7): 15-29.
[2]	尤肖虎, 潘志文, 高西奇 ,等. 5G移动通信发展趋势与若干关键技术[J]. 中国科学:信息科学, 2014,44(5): 551-563.
	YOU X H , PAN Z W , GAO X Q ,et al. The 5G mobile communication:the development trends and its emerging key techniques[J]. SCIENTIA SINICA Informationis, 2014,44(5): 551-563.
[3]	赵国锋, 陈婧, 韩远兵 ,等. 5G移动通信网络关键技术综述[J]. 重庆邮电大学学报(自然科学版), 2015,27(4): 441-452.
	ZHAO G F , CHEN J , HAN Y B ,et al. Prospective network techniques for 5G mobile communication:a survey[J]. Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), 2015,27(4): 441-452.
[4]	KHODASHENAS P S , AZNAR J , LEGARREA A ,et al. 5G network challenges and realization insights[C]// 2016 18th International Conference on Transparent Optical Networks (ICTON). Piscataway:IEEE Press, 2016: 1-4.
[5]	华楠, 郑小平 . 智能光网络发展历程的回顾和展望:从ASON到PCE,再到SDON[J]. 电信科学, 2014,30(2): 88-98.
	HUA N , ZHENG X P . Review and outlook of the development course of intelligent optical networks:from ASON to PCE and then to SDON[J]. Telecommunications Science, 2014,30(2): 88-98.
[6]	李少晖, 沈世奎 . 光网络性能监测技术[J]. 电信网技术, 2012(12): 9-14.
	LI S H , SHEN S K . Optical network performance monitoring technology[J]. Telecommunications Network Technology, 2012(12): 9-14.
[7]	张肃, 王目光 . 基于广义回归神经网络的色散和OSNR监测[J]. 光电技术应用, 2018,33(1): 30-35+70.
	ZHANG S , WANG M G . Chromatic dispersion and OSNR monitoring based on generalized regression neural network[J]. Electro-optic Technology Application, 2018,33(1): 30-35+70.
[8]	YU J , MO W , HUANG Y K ,et al. Model transfer of QoT prediction in optical networks based on artificial neural networks[J]. IEEE/OSA Journal of Optical Communications and Networking, 2019,11(10): 48-57.
[9]	GHOBADI M , MAHAJAN R . Optical layer failures in a large backbone[C]// Proceedings of the 2016 Internet Measurement Conference. New York:ACM Press, 2016: 461-467.
[10]	ROTTONDI C , BARLETTA L , GIUSTI A ,et al. Machine-learning method for quality of transmission prediction of unestablished lightpaths[J]. Journal of Optical Communications and Networking, 2018,10(2): 286-297.
[11]	鄢然, 郑豪, 李蔚 . 基于机器学习的光链路建立中的传输质量预测技术[J]. 光通信技术, 2020,44(6): 15-19.
	YAN R , ZHENG H , LI W . Transmission quality prediction technology in optical link building based on machine learning[J]. Optical Communication Technology, 2020,44(6): 15-19.
[12]	MORAIS R M , PEDRO J . Machine learning models for estimating quality of transmission in DWDM networks[J]. Journal of Optical Communications and Networking, 2018,10(10): 84-99.
[13]	GAO Z , YAN S , ZHANG J ,et al. ANN-based multi-channel QoT-prediction over a 563.4-km field-trial testbed[J]. Journal of Lightwave Technology, 2020,38(9): 2646-2655.
[14]	曹莹, 苗启广, 刘家辰 ,等. AdaBoost算法研究进展与展望[J]. 自动化学报, 2013,39(6): 745-758.
	CAO Y , MIAO Q G , LIU J C ,et al. Advance and prospects of AdaBoost algorithm[J]. Acta Automatica Sinica, 2013,39(6): 745-758.
[15]	于玲, 吴铁军 . 集成学习:Boosting 算法综述[J]. 模式识别与人工智能, 2004,17(1): 52-59.
	YU L , WU T J . Assemble learning:a survey of boosting algorithms[J]. Pattern Recognition and Artificial Intelligence, 2004,17(1): 52-59.
[16]	LARADJI I H , ALSHAVEB M , GHOUTI L . Software defect prediction using ensemble learning on selected features[J]. Information and Software Technology, 2015,58: 388-402.
[17]	RIBEIRO M H D M , DOS S C L . Ensemble approach based on bagging,boosting and stacking for short-term prediction in agribusiness time series[J]. Applied Soft Computing, 202086: 105837-105866.
[18]	PARK Y S , LEK S . Artificial neural networks:multilayer perceptron for ecological modeling[J]. Developments in Environmental Modelling, 2016,28: 123-140.

结构	迭代次数/次	学习速率	验证方法
MLP₁	101	5×10^-4	五折交叉验证
MLP₂	151	2×10^-4	五折交叉验证
MLP₃	151	4×10^-4	五折交叉验证
MLP₄	201	3×10^-4	五折交叉验证
MLP₅	101	4×10^-4	五折交叉验证
MLP₆	1	1×10^-4	五折交叉验证

模型	MAE	MSE
ANN	0.023 4	1.238 9×10^-3
EL-MLP	0.004 1	2.630 0×10^-5

模型	标准	场景1	场景2	场景3	场景4
ANN	MAE	0.043 7	0.029 8	0.040 1	0.047 0
EL-MLP	MAE	0.005 5	0.004 4	0.005 1	0.004 7
ANN	MSE (×10^-3)	3.192 0	1.558 1	2.970 3	3.682 2
EL-MLP	MSE (×10^-5)	5.196 2	3.505 7	4.888 3	4.765 1

基于集成学习的广域光骨干网多信道传输质量预测方法

Multi-channel QoT prediction method in wide-area optical backbone network based on ensemble learning

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 18

相关文章 15

Metrics

推荐阅读 0

[1]	戴千一, 张斌, 郭松, 徐开勇. 基于多分类器集成的区块链网络层异常流量检测方法[J]. 通信学报, 2023, 44(3): 66-80.
[2]	何遵文, 侯帅, 张万成, 张焱. 通信特定辐射源识别的多特征融合分类方法[J]. 通信学报, 2021, 42(2): 103-112.
[3]	郝晓辰,王立元,刘金硕,解力霞,张文焕. WSN中基于双群体差分进化的资源分配优化算法[J]. 通信学报, 2018, 39(4): 68-75.
[4]	崔颖,徐凯,陆忠军,刘述彬,王立国. 主动学习策略融合算法在高光谱图像分类中的应用[J]. 通信学报, 2018, 39(4): 91-99.
[5]	赵泽,高源,崔莉. VehLoc：基于低功耗蓝牙多信道RSSI值的车内高精度定位方法[J]. 通信学报, 2018, 39(12): 47-59.
[6]	宋彩霞,谭国真,丁男. 车载自组织网络中RSU协调的多信道MAC协议[J]. 通信学报, 2018, 39(11): 10-22.
[7]	邓清勇,裴廷睿,李哲涛,刘安丰,邓亚风. 多接口协作的高吞吐多信道MAC协议[J]. 通信学报, 2017, 38(8): 50-59.
[8]	冯景瑜,杜续,王宏刚,黄文华. 认知ad hoc网络中的多信道路由安全威胁及其对策研究[J]. 通信学报, 2016, 37(Z1): 92-97.
[9]	宋彩霞,谭国真,丁男,步俊凌,张福新,刘明剑. 面向应用的车载自组织网络跨层多信道MAC协议[J]. 通信学报, 2016, 37(5): 95-105.
[10]	余晓东,雷英杰,宋亚飞,岳韶华,胡军红. 基于直觉模糊核匹配追踪集成的目标识别方法[J]. 通信学报, 2015, 36(10): 165-171.
[11]	程宾,慈林林,田成平,杨明华. 基于网络分割的无线传感器网络多信道MAC协议[J]. 通信学报, 2014, 35(Z2): 165-171.
[12]	程宾，慈林林，田成平，杨明华. 基于网络分割的无线传感器网络多信道MAC协议[J]. 通信学报, 2014, 35(Z2): 22-171.
[13]	李西洋,范平志. 移动自组织网络中的多信道MAC调度码的设计与分析[J]. 通信学报, 2014, 35(5): 57-64.
[14]	李西洋1,2，范平志2. 移动自组织网络中的多信道MAC调度码的设计与分析[J]. 通信学报, 2014, 35(5): 8-64.
[15]	王亮，盛敏，张琰，马骁. 基于信道状态感知的多信道认知多址接入协议[J]. 通信学报, 2014, 35(4): 8-73.