Optical Network Traffic Prediction Based on Graph Convolutional Neural Networks

被引：0
|
作者：
Gui, Yihan [1 ]
Wang, Danshi [1 ]
Guan, Luyao [1 ]
Zhang, Min [1 ]
机构：
[1] Beijing Univ Posts & Telecommun, State Key Lab Informat Photon & Opt Commun, Beijing, Peoples R China
来源：
2020 OPTO-ELECTRONICS AND COMMUNICATIONS CONFERENCE (OECC 2020) | 2020年
基金：
中国国家自然科学基金;
关键词：
Traffic prediction; elastics optical networks; spatial-temporal dependence; graph convolutional network;
D O I：
暂无
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
Understanding traffic patterns in largescale networks is of great importance for optical networks to implement intelligent management and adaptive adjustment. However, accurate traffic prediction in flexible optical networks is challenging because of the temporal and spatial autocorrelation of traffic. Spatial-temporal graph modeling is an effective approach to analyze the spatial relations and temporal trends of traffic in a system. We propose an efficient graph-based neural network named as the graph convolutional network with the gated recurrent unit (GCN-GRU). Based on a real-world optical networking traffic dataset, 98% accuracy for traffic prediction is achieved by GCN-GRU.
引用
收藏
页数：3
相关论文
共 50 条
  • [31] Prediction of Cellular Network Channel Utilization Based on Graph Convolutional Networks
    Zhu, Rui
    Luo, Xingshuang
    Yao, Jiayi
    Zhu, Xinning
    Zhang, Chunhong
    2022 IEEE 33RD ANNUAL INTERNATIONAL SYMPOSIUM ON PERSONAL, INDOOR AND MOBILE RADIO COMMUNICATIONS (IEEE PIMRC), 2022, : 1233 - 1238
  • [32] Cellular Network Traffic Prediction with Hybrid Graph Convolutional Recurrent Network
    Zhang, Miaoru
    Zhou, Hao
    Yu, Ke
    Wu, Xiaofei
    WIRELESS PERSONAL COMMUNICATIONS, 2024, 138 (03) : 1867 - 1892
  • [33] Cellular Network Traffic Prediction with Hybrid Graph Convolutional Recurrent Network
    Zhang, Miaoru
    Zhou, Hao
    Yu, Ke
    Wu, Xiaofei
    Wireless Personal Communications, 138 (03): : 1867 - 1892
  • [34] Simpler is better: Multilevel Abstraction with Graph Convolutional Recurrent Neural Network Cells for Traffic Prediction
    Roudbari, Naghmeh Shafiee
    Patterson, Zachary
    Eicker, Ursula
    Poullis, Charalambos
    2022 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2022, : 61 - 70
  • [35] Revisiting Random Forests in a Comparative Evaluation of Graph Convolutional Neural Network Variants for Traffic Prediction
    Ting, Ta Jiun
    Li, Xiaocan
    Sanner, Scott
    Abdulhai, Baher
    2021 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2021, : 1259 - 1265
  • [36] Spatiotemporal graph convolutional recurrent networks for traffic matrix prediction
    Zhao, Jianlong
    Qu, Hua
    Zhao, Jihong
    Dai, Huijun
    Jiang, Dingchao
    TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES, 2020, 31 (11):
  • [37] Spatiotemporal Data Fusion in Graph Convolutional Networks for Traffic Prediction
    Zhao, Baoxin
    Gao, Xitong
    Liu, Jianqi
    Zhao, Juanjuan
    Xu, Chengzhong
    IEEE ACCESS, 2020, 8 : 76632 - 76641
  • [38] Short-term Network-wide Traffic Prediction Based on Graph Convolutional Network
    Chen X.-Q.
    Zhou L.-X.
    Cao Z.
    Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology, 2020, 20 (04): : 49 - 55
  • [39] Network traffic prediction based on feature fusion spatio-temporal graph convolutional network
    Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing
    100876, China
    不详
    100876, China
    Proc SPIE Int Soc Opt Eng,
  • [40] A Graph Convolutional Neural Network Model for Trajectory Prediction
    Di, Zichao
    Zhou, Yue
    Chen, Kun
    Chen, Zongzhi
    THIRTEENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2021), 2022, 12083
12345