Traffic Prediction of Space-Integrated-Ground Information Network Based on Improved LSTM Algorithm

Chengsheng PAN; Yufu WANG; Li YANG

doi:10.11959/j.issn.2096-8930.20200208

您当前的位置：

首页 >

文章列表页 >

Traffic Prediction of Space-Integrated-Ground Information Network Based on Improved LSTM Algorithm

Topics: Architecture of Space-Integrated-Ground Information Network | 更新时间：2024-06-03

- Traffic Prediction of Space-Integrated-Ground Information Network Based on Improved LSTM Algorithm
- Space-Integrated-Ground Information Networks Vol. 1, Issue 2, Pages: 57-65(2020)
- 作者机构：
  
  1. 大连大学通信与网络重点实验室，辽宁大连 116622
  2. 南京信息工程大学，江苏南京 210044
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.2096-8930.20200208
  CLC： TN929
- Published Online：2020-12，
  
  Published：20 December 2020
- 稿件说明：
移动端阅览
Chengsheng PAN, Yufu WANG, Li YANG. Traffic Prediction of Space-Integrated-Ground Information Network Based on Improved LSTM Algorithm[J]. Space-integrated-ground information networks, 2020, 1(2): 57-65.
DOI：

Chengsheng PAN, Yufu WANG, Li YANG. Traffic Prediction of Space-Integrated-Ground Information Network Based on Improved LSTM Algorithm[J]. Space-integrated-ground information networks, 2020, 1(2): 57-65. DOI： 10.11959/j.issn.2096-8930.20200208.

摘要

天地一体化信息网络由于存在流量突发性强、拓扑时变等问题使得通信易产生中断，流量波动不平稳导致其流量预测难度远高于地面网络。针对该问题，提出一种改进的LSTM算法，首先分析流量序列滞后变量对预测值的影响，判断流量自相关度；其次，采用以预测值代替中断的方式，消除训练集的噪声和断点；最后，使用Dropout算法减少了噪声和神经网络过拟合带来的影响，准确预测天地一体化信息网络流量数据。仿真实验表明，在OPNET仿真环境中，该算法相较于其他算法准确性提升了59.21%，算法训练速度提升了11.11%，能够为天地一体化信息网络统筹调度提供有效的数据支撑。

Abstract

The space-integrated-ground information network is easy to interrupt and the traffi c fl uctuation is not stable due to the problems of high traffi c burst and topological time-varying

which makes the traffi c prediction diffi cult much higher than the ground.In order to solve this problem

an improved LSTM algorithm was put forward.Firstly

the traffi c autocorrelation was judged by analyzd the infl uence of the lag variable of traffi c sequence on the predicted value; Secondly

the noise and breakpoint of the training set were eliminated by replacing the interruption with the predicted value; Finally

Dropout algorithm was used to reduce the impact of noise and neural network over fi tting

and accurately predict the traffi c data of the integrated intelligent network.The simulation results showed that in OPNET simulation environment

compared with other algorithms

the accuracy of this algorithm was improved by 59.21%

and the training speed of the algorithm was improved by 11.11%

which could provide eff ective data support for the overall scheduling of the integrated intelligent network.

关键词

Keywords

references

成艳 , 韩笑冬 , 陈亮亮 , 等 . 天地一体化信息网络参考模型及关键技术 [J ] . 空间电子技术 , 2017 ( 4 ): 39 - 42 + 47 .

CHENG Y , HAN X D , CHEN L L , et al . Function reference model and key technologies of space-integration ground information network [J ] . Space Electronic Technology , 2017 ( 4 ): 39 - 42 + 47 .

刘立祥 . 天地一体化信息网络 [M ] . 北京 : 科学出版社 , 2015 .

LIU L X . Space-and-ground integration network [M ] . Beijing : Science Press , 2015 .

林振荣 , 黎嘉诚 , 杨冬芹 , 等 . 改进微分进化和小波神经网络的网络流量预测 [J ] . 计算机工程与设计 , 2019 , 040 ( 12 ): 3413 - 3418 .

LIN Z R , LI J C , YANG D Q , et al . Network traffic prediction based on wavelet neural network with improved differential evolution algorithm [J ] . Computer Engineering and Design , 2019 , 040 ( 12 ): 3413 - 3418 .

LI M , WANG Y W , WANG Z W , et al . A deep learning method based on an attention mechanism for wireless network traffic prediction [J ] . Ad Hoc Networks , 2020 .

穆昌 . 基于小波变换和极限学习机的网络流量预测模型 [J ] . 微型电脑应用 , 2020 , 036 ( 1 ): 138 - 140 .

MU C . Network traffic prediction model based on wavelet transform and limit learning machine [J ] . Microcomputer Applications , 2020 , 036 ( 1 ): 138 - 140 .

FAN J , MU D , LIU Y . Research on network traffic prediction model based on neural network [C ] // 2019 2nd International Conference on Information Systems and Computer Aided Education(ICISCAE) . Piscataway: IEEE , 2019 : 554 - 557 .

ZHANG G , HUANG D . Short-term network traffic prediction with ACD and particle filter [C ] // 2013 5th International Conference on Intelligent Networking and Collaborative Systems . Piscataway:IEEE , 2013 : 189 - 191 .

LI Z , LEI Q , KOUYING X , et al . A novel BP neural network model for traffic prediction of next generation network [C ] // 2009 Fifth International Conference on Natural Computation . Piscataway:IEEE , 2009 : 32 - 38 .

KO T , RAZA S M , BINH D T , et al . Network prediction with traffic gradient classification using convolutional neural networks [C ] // 2020 14th International Conference on Ubiquitous Information Management and Communication (IMCOM) . Piscataway:IEEE , 2020 : 1 - 4 .

MOHORCIC M , SVIGELJ A , KANDUS G , et al . Demographically weighted traffic flow models for adaptive routing in packet-switched non-geostationary satellite meshed networks [J ] . Computer Networks the International Journal of Computer ＆Telecommunications Networking , 2003 , 43 ( 2 ): 113 - 131 .

DONNER A , KISSLING C , HERMENIER R . Satellite constellation networks for aeronautical communication:Traffic modelling and link load analysis [J ] . Iet Communications , 2010 , 4 ( 13 ): 1594 - 1606 .

CHEN Q , . Traffic prediction based on surrogate model in satellite constellation networks [C ] // 2019 12th IFIP Wireless and Mobile Networking Conference (WMNC) . Piscataway: IEEE , 2019 : 126 - 130 .

刑梦来 , 王硕 , 孙洋洋 . 深度学习框架PyTorch快速开发与实战 [M ] . 北京 : 电子工业出版社 , 2018 .

XING M L , WANG S , SUN Y Y . Rapid development and practice of deep learning framework PyTorch [M ] . Beijing : Publishing House of Electronics Industry , 2018 .

CHEN K , SONG X , HAN D , et al . Pedestrian behavior prediction model with a convolutional LSTM encoder-decoder [J ] . Physica A:Statal Mechanics and its Applications , 2020 : 125 - 132 .

SRIVASTAVA N , HINTON G E , KRIZHEVSKY A , et al . Dropout:a simple way to prevent neural networks from overfitting [J ] . Journal of Machine Learning Research , 2014 , 15 ( 1 ): 1929 - 1958 .

Views

796

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Endogenous Security for the Space-Integrated-Ground Information Network in 6G

CNN-Based Channel Estimation Method for OTFS System in Satellite-Ground Scenario

Research on Key Technologies and Design of High-peed Transmission Protocol in Space-Integrated-Ground Information Network

Research on Network Architecture for the Space-Integrated-Ground Information Network in 6G

Attack Analysis Framework of Space-Integrated-Ground Information Network Based on Cybersecurity Knowledge Graph

Related Author

Wei YOU

Yajun CHEN

Jiangxing WU

Kaizhi HUANG

Xinsheng JI

Cheng GUO

Le YU

Lidong ZHU

Related Institution

Purple Mountain Laboratories: Networking, Communications and Security

National Digital Switching System Engineering and Technological R＆D Center

China Electronic Device Systems Engineering Corporation

National University of Defense Technology

Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China 3.School of Cyber Security, University of Chinese Academy of Sciences

⁰