Acta Metallurgica Sinica(English letters) ›› 2013, Vol. 20 ›› Issue (1): 19-25.doi: 10.1016/S1005-8885(13)60003-5

• Networks • 上一篇    下一篇

Dynamic modeling approach to analyze user churn in a large P2P downloading system

黄丹,郑毅,陈常嘉   

  1. 北京交通大学
  • 收稿日期:2012-08-21 修回日期:2012-12-03 出版日期:2013-02-28 发布日期:2013-02-28
  • 通讯作者: 黄丹 E-mail:daisy.huangdan@gmail.com
  • 基金资助:

    This work was supported by the National Natural Science Foundation of China (61271199), and the Fundamental Research Funds in Beijing Jiaotong University (W11JB00630).

Dynamic modeling approach to analyze user churn in a large P2P downloading system

  1. School of Electronics and Information Engineering, Beijing Jiaotong University, Beijing 100044, China
  • Received:2012-08-21 Revised:2012-12-03 Online:2013-02-28 Published:2013-02-28
  • Contact: Dan Huang E-mail:daisy.huangdan@gmail.com
  • Supported by:

    This work was supported by the National Natural Science Foundation of China (61271199), and the Fundamental Research Funds in Beijing Jiaotong University (W11JB00630).

摘要:

Characterizing the features of user churn is crucial to the sustainable development of peer-to-peer (P2P) systems where peers join and leave at any arbitrary time. This paper analyzes the user churn in a P2P downloading system named QQXuanfeng by using the fine-grained log analysis over 60 days. It shows that the online and offline duration is related to up (arrive) time and down (depart) time respectively. A continuous ON/OFF process, which exhibits the diurnal patterns of users, is simulated using the churn model. In particular, the dynamic departure rate is proposed to give insight into the distribution of online duration. Further more, considering the heterogeneity of users, we cluster users based on the similarity of redefined user availability. As an example of application of this model, a high availability overlay is constructed and evaluated based on the clustering.

关键词:

P2P network, user churn, clustering

Abstract:

Characterizing the features of user churn is crucial to the sustainable development of peer-to-peer (P2P) systems where peers join and leave at any arbitrary time. This paper analyzes the user churn in a P2P downloading system named QQXuanfeng by using the fine-grained log analysis over 60 days. It shows that the online and offline duration is related to up (arrive) time and down (depart) time respectively. A continuous ON/OFF process, which exhibits the diurnal patterns of users, is simulated using the churn model. In particular, the dynamic departure rate is proposed to give insight into the distribution of online duration. Further more, considering the heterogeneity of users, we cluster users based on the similarity of redefined user availability. As an example of application of this model, a high availability overlay is constructed and evaluated based on the clustering.

Key words:

P2P network, user churn, clustering