Method and device for predicting residual online time of peer in peer-to-peer network

• US 8,280,705 B2
• Filed: 07/13/2010
• Issued: 10/02/2012
• Est. Priority Date: 01/23/2008
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Inventors: Shi, Guangyu, Gong, Hao
• Primary Examiner(s): Thangavelu, Kandasamy
• Assistant Examiner(s): MOLL, NITHYA JANAKIRAMAN
• Application Number:
  US12/835,400
• Publication Number:
  US 20100280804A1
• Time in Patent Office: 812 Days
• Field of Search: 703/2, 703/22
• US Class Current: 703/2
• CPC Class Codes: H04L 67/104 Peer-to-peer [P2P] networks
• CPC Class Codes: H04L 67/1048 Departure or maintenance mechanisms

Abstract

A method for predicting a residual online time of a peer in a peer-to-peer (P2P) network is provided. The method includes: obtaining M history life cycle sampling data S_i of a peer, i=1, . . . , M; determining the number, n, of Gaussian components in a multidimensional Gaussian Mixture Model to be established, where n≧2, and the multidimensional Gaussian Mixture Model denotes a probability distribution of a residual online time of the peer; using S_i and n to establish the multidimensional Gaussian Mixture Model; and using the established multidimensional Gaussian Mixture Model to predict the residual online time of the peer. A device for predicting a residual online time of a peer in a P2P network is also provided.

Claims

1. A method for predicting a residual online time of a peer in a peer-to-peer (P2P) network, the method comprising:

obtaining, by a peer node in the P2P network, M history life cycle sampling data S_i of the peer node, wherein i=1 to M and the history life cycle sampling data comprises a history starting online time point and a history online time of the peer node;

determining, by the peer node in the P2P network, Gaussian components n in a multidimensional Gaussian Mixture Model to be established, wherein n is a positive integer greater than or equal to 2, and the multidimensional Gaussian Mixture Model denotes a probability distribution of the residual online time of the peer node;

utilizing, by the peer node in the P2P network, S_i and n to establish a multidimensional Gaussian Mixture Model; and

predicting, by the peer node in the P2P network, the residual online time of the peer node by utilizing the multidimensional Gaussian Mixture Model.

2. The method according to claim 1, wherein contents of the history life cycle sampling data further comprise:

history online time information of the peer node, history starting online time point information of the peer node, and history online interval information of the peer node.

3. The method according to claim 1, wherein the obtaining M history life cycle sampling data S_i of the peer node comprises:

obtaining, by the peer node in the P2P network, M history life cycle source data P_i of the peer, wherein i=1 to M; and

sampling, by the peer node in the P2P network, the source data P_i according to a sampling precision to obtain the history life cycle sampling data S_i.

4. The method according to claim 3, wherein the history life cycle sampling data or history life cycle source data are recorded and kept by the peer itself, or obtained concentratedly by enabling a peer node to send the history life cycle sampling data or history life cycle source data to a central server.

5. The method according to claim 1, wherein after the process of predicting the residual online time of the peer node, the method further comprises:

calculating, by the peer node in the P2P network, a current surviving life cycle of the peer or a probability that a residual online time possibly occurs according to the predicted residual online time and an elapsed online time of the peer node.