QQ登录

只需要一步,快速开始

 注册地址  找回密码
查看: 2671|回复: 0
打印 上一主题 下一主题

[其他资源] RouteNet: Leveraging Graph Neural Networks for Network Modeling and Optimizat...

[复制链接]
字体大小: 正常 放大
杨利霞        

5273

主题

82

听众

17万

积分

  • TA的每日心情
    开心
    2021-8-11 17:59
  • 签到天数: 17 天

    [LV.4]偶尔看看III

    网络挑战赛参赛者

    网络挑战赛参赛者

    自我介绍
    本人女,毕业于内蒙古科技大学,担任文职专业,毕业专业英语。

    群组2018美赛大象算法课程

    群组2018美赛护航培训课程

    群组2019年 数学中国站长建

    群组2019年数据分析师课程

    群组2018年大象老师国赛优

    跳转到指定楼层
    1#
    发表于 2020-11-16 15:20 |只看该作者 |倒序浏览
    |招呼Ta 关注Ta
    RouteNet: Leveraging Graph Neural Networks for

    & J" L7 V4 g$ `
    Network Modeling and Optimization in SDN

    $ @5 l! h9 P# l" W$ D" I+ [8 S- e* j9 ^6 ^2 ]2 ~9 p' b) @! S( u
    7 K# E) o* u/ H/ }( D6 d
    Network modeling is a key enabler to achieve/ y! a3 g+ y' s9 H/ v+ q
    effificient network operation in future self-driving Software
    8 U; |1 c0 Z; V4 fDefifined Networks. However, we still lack functional network7 a) S- y4 x% l! ~" j8 ]$ p! `. ?
    models able to produce accurate predictions of Key Performance
    ! G6 u: ]5 g7 f9 N0 {1 ^, H; zIndicators (KPI) such as delay, jitter or loss at limited cost.% T+ q& e- m3 l9 T, J6 a
    In this paper we propose RouteNet, a novel network model based3 U; V* D! @- B" |5 z: E7 \+ j
    on Graph Neural Network (GNN) that is able to understand
    4 ?8 I6 D. V; A/ x. ?3 i/ Ethe complex relationship between topology, routing, and input/ V" ?3 V# U. Y' ?4 K
    traffific to produce accurate estimates of the per-source/destination1 s0 W5 p- G& y1 U  E: c' H
    per-packet delay distribution and loss. RouteNet leverages the1 J" d3 W8 H$ T4 M$ v/ |6 h
    ability of GNNs to learn and model graph-structured information( E, ]8 M9 i% e/ ~: j  r
    and as a result, our model is able to generalize over arbitrary
    : n, ]8 p. l3 H; C- Ttopologies, routing schemes and traffific intensity. In our eval
    4 x; a7 c. C$ u$ I& I+ b  huation, we show that RouteNet is able to predict accurately
    7 R: t# J; E0 j: h! lthe delay distribution (mean delay and jitter) and loss even in
    % w+ x. E& |! G! r1 Gtopologies, routing and traffific unseen in the training (worst case0 C* V9 F$ K% m
    MRE = 15.4%). Also, we present several use cases where we3 ^6 H+ |9 v$ h' E
    leverage the KPI predictions of our GNN model to achieve
    ; m6 O+ W" ?; i' J8 u. x( Jeffificient routing optimization and network planning.
    1 N8 T  x/ W$ A; o4 w" W; ^9 N4 [, m
    3 [! p" j/ }) m

    08934670.pdf

    999 KB, 下载次数: 0, 下载积分: 体力 -2 点

    zan
    转播转播0 分享淘帖0 分享分享0 收藏收藏0 支持支持0 反对反对0 微信微信
    您需要登录后才可以回帖 登录 | 注册地址

    qq
    收缩
    • 电话咨询

    • 04714969085
    fastpost

    关于我们| 联系我们| 诚征英才| 对外合作| 产品服务| QQ

    手机版|Archiver| |繁體中文 手机客户端  

    蒙公网安备 15010502000194号

    Powered by Discuz! X2.5   © 2001-2013 数学建模网-数学中国 ( 蒙ICP备14002410号-3 蒙BBS备-0002号 )     论坛法律顾问:王兆丰

    GMT+8, 2026-6-11 12:15 , Processed in 0.289967 second(s), 54 queries .

    回顶部