Articles producció científica> Enginyeria Informàtica i Matemàtiques

Tracking and Predicting End-to-End Quality in Wireless Community Networks

  • Identification data

    Identifier: imarina:5657912
    Authors:
    Millan PMolina CDimogerontakis ENavarro LMeseguer RBraem BBlondia C
    Abstract:
    © 2015 IEEE. Community networks are an emergent model with mottos like 'a free net for everyone is possible' or 'don't buy the network, be the network'. Their social impact is measurable, as the community is provided with the right and opportunity of communication. The combination of wired and wireless links in these networks, and the unreliable nature of the wireless medium, poses several challenges to the routing protocol. End-to End quality tracking helps the routing layer to select paths that maximize the delivery rate and minimize traffic congestion. We believe that End-to-End quality prediction can be a technique that surpasses End-to-End quality tracking by foreseeing which paths are more likely to change quality. In this work, we focus on End-to-End quality prediction by means of time-series analysis. We apply this prediction technique in the routing layer of large scale, distributed, and decentralized networks. We demonstrate that it is possible to accurately predict End-to-End Quality with an average Mean Absolute Error of just 2.4%. Particularly, we analyze the path properties and path ETX behavior to identify the best prediction algorithm. Moreover, we analyze the EtEQ prediction accuracy some steps ahead in the future and also its dependency of the time of the day.
  • Others:

    Author, as appears in the article.: Millan P; Molina C; Dimogerontakis E; Navarro L; Meseguer R; Braem B; Blondia C
    Department: Enginyeria Informàtica i Matemàtiques
    URV's Author/s: Millán Marco, Pedro / MOLINA LLAURADÓ, CRISTINA MISERICÒRDIA
    Keywords: Time-series analysis End-to-end quality prediction Community networks
    Abstract: © 2015 IEEE. Community networks are an emergent model with mottos like 'a free net for everyone is possible' or 'don't buy the network, be the network'. Their social impact is measurable, as the community is provided with the right and opportunity of communication. The combination of wired and wireless links in these networks, and the unreliable nature of the wireless medium, poses several challenges to the routing protocol. End-to End quality tracking helps the routing layer to select paths that maximize the delivery rate and minimize traffic congestion. We believe that End-to-End quality prediction can be a technique that surpasses End-to-End quality tracking by foreseeing which paths are more likely to change quality. In this work, we focus on End-to-End quality prediction by means of time-series analysis. We apply this prediction technique in the routing layer of large scale, distributed, and decentralized networks. We demonstrate that it is possible to accurately predict End-to-End Quality with an average Mean Absolute Error of just 2.4%. Particularly, we analyze the path properties and path ETX behavior to identify the best prediction algorithm. Moreover, we analyze the EtEQ prediction accuracy some steps ahead in the future and also its dependency of the time of the day.
    Thematic Areas: Electrical and electronic engineering Artificial intelligence
    ISSN: 9781467381031
    Author's mail: pere.millan@urv.cat
    Author identifier: 0000-0002-4132-7099
    Record's date: 2024-10-12
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Proceedings - 2015 International Conference On Future Internet Of Things And Cloud, Ficloud 2015 And 2015 International Conference On Open And Big Data, Obd 2015. 794-799
    APA: Millan P; Molina C; Dimogerontakis E; Navarro L; Meseguer R; Braem B; Blondia C (2015). Tracking and Predicting End-to-End Quality in Wireless Community Networks.
    Article's DOI: 10.1109/FiCloud.2015.96
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2015
    Publication Type: Proceedings Paper
  • Keywords:

    Artificial Intelligence,Electrical and Electronic Engineering
    Time-series analysis
    End-to-end quality prediction
    Community networks
    Electrical and electronic engineering
    Artificial intelligence
  • Documents:

  • Cerca a google

    Search to google scholar