원문정보
초록
영어
With the rapid development of P2P technology, P2P IPTV applications have received more and more attention. And program-list distribution is very important to P2P IPTV applications. In order to collect IPTV program information, a distributed multi-protocol crawler was proposed based on principle of program-list distribution. The IPTV programs information will be used for characteristic analyses of program and for automatic sorting of program and establishment of IPTV repository in next work. In addition, a task scheduling model based on fuzzy control is introduced to improve performance of the crawler. In the experiment, three task scheduling algorithms are compared, and the results show that the fuzzy algorithm can balance service nodes’ load effectively with less task execution time.
목차
1. Introduction
2. Crawling Mechanism
2.1. Principle of Program-list Distribution
2.2. Architecture of DMP-Crawler
3. Task Scheduling Model Based on Fuzzy Control
3.1. Fuzzy Model of Dynamic Performance of Service Nodes
3.2. Fuzzy Model of Task Request Load
3.3. Defuzzification
3.4. Inference Rules
3.5. Task Scheduling Process of DMP-Crawler
4. Results and Analysis
4.1. Load of SNs
4.2. Execution Time of Tasks
5. Conclusion
Acknowledgements
References