End-to-end quality of service seen by applications A statistical learning approach

被引：3
作者：
Belzarena, Pablo [1 ]
Aspirot, Laura [2 ]
机构：
[1] Univ Republica, Fac Ingn, Elect Engn Dept 3, Montevideo, Uruguay
[2] Univ Republica, Fac Ingn, Dept Math Stat, Montevideo, Uruguay
来源：
COMPUTER NETWORKS | 2010年 / 54卷 / 17期
关键词：
End to end active measurements; Statistical learning; Nadaraya-Watson; Support Vector Machines; QoS; MULTICAST-BASED INFERENCE; FUNCTIONAL DATA; TIME-SERIES; REGRESSION; PREDICTION; DYNAMICS;
D O I：
10.1016/j.comnet.2010.06.004
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
The focus of this work is on the estimation of quality of service (QoS) parameters seen by an application Our proposal is based on end-to-end active measurements and statistical learning tools We propose a methodology where the system is trained during short periods with application flows and probe packets bursts We learn the relation between QoS parameters seen by the application and the state of the network path which is Inferred from the interarrival times of the probe packets bursts We obtain a continuous non intrusive QoS monitoring methodology We propose two different estimators of the network state and analyze them using Nadaraya-Watson estimator and Support Vector Machines (SVM) for regression We compare these approaches and we show results obtained by simulations and by measures in operational networks (C) 2010 Elsevier B V All rights reserved
引用
收藏
页码：3123 / 3143
页数：21
相关论文
共 50 条
  • [31] Online based learning for predictive end-to-end network slicing in 5G networks
    Bouzidi, El Hocine
    Outtagarts, Abdelkader
    Hebbar, Abdelkrim
    Langar, Rami
    Boutaba, Raouf
    ICC 2020 - 2020 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC), 2020,
  • [32] Bounds on end-to-end statistical delay and jitter in multiple multicast coded packet networks
    Raayatpanah, M. A.
    Fathabadi, H. Salehi
    Khalaj, B. H.
    Khodayifar, S.
    Pardalos, P. M.
    JOURNAL OF NETWORK AND COMPUTER APPLICATIONS, 2014, 41 : 217 - 227
  • [33] Network Slicing in Industry 4.0 Applications: Abstraction Methods and End-to-End Analysis
    Kalor, Anders Ellersgaard
    Guillaume, Rene
    Nielsen, Jimmy Jessen
    Mueller, Andreas
    Popovski, Petar
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2018, 14 (12) : 5419 - 5427
  • [34] GMPLS-based VPN service to realize end-to-end QoS and resilient paths
    Matsuura, Hiroshi
    Takami, Kazumasa
    MANAGEMENT OF CONVERGENCE NETWORKS AND SERVICES, PROCEEDINGS, 2006, 4238 : 302 - 311
  • [35] End-to-End Wireless Network Performance Evaluation Based on Application Quality Indicators
    Chheda, Deven
    Prasad, Abhijeet
    Abd El-Samiea, Mohamed
    Long Duan
    Nsofu, Mubanga
    Handoo, Arun
    Mittal, Mukesh
    2018 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2018,
  • [36] End-to-End Quality of Services Issues in 4G Mobile Networks
    Sarraf, Charles M.
    Ousta, Firas
    COMPUTATIONAL ENGINEERING IN SYSTEMS APPLICATIONS, 2008, : 236 - 242
  • [37] Vertical Handover Control Considering End-to-End Communication Quality in IP Mobility
    Hourai, Takuya
    Maeda, Kaori
    Ohishi, Yasuhiro
    Morihiro, Hayato
    Harase, Tomoki
    2012 IEEE/IPSJ 12TH INTERNATIONAL SYMPOSIUM ON APPLICATIONS AND THE INTERNET (SAINT), 2012, : 332 - 337
  • [38] End-to-end deep learning for pollutant prediction using street view images
    Wu, Lijie
    Liu, Xiansheng
    Zhang, Xun
    Wang, Rui
    Guo, Zhihao
    URBAN CLIMATE, 2025, 60
  • [39] End-to-end quality management method for VoIP speech using RTCP XR
    Masuda, Masataka
    Furukawa, Tsuyoshi
    Hayashi, Takanori
    Majima, Souhei
    IEICE TRANSACTIONS ON COMMUNICATIONS, 2007, E90B (11) : 3073 - 3082
  • [40] End-to-end deep representation learning for time series clustering: a comparative study
    Baptiste Lafabregue
    Jonathan Weber
    Pierre Gançarski
    Germain Forestier
    Data Mining and Knowledge Discovery, 2022, 36 : 29 - 81
12345