Demand forecast and performance prediction in peer-assisted on-demand streaming systems
Demand forecast and performance prediction in peer-assisted on-demand streaming systems
复制标题
DOI：
10.1109/infcom.2011.5935196
复制
发表时间：
2011-04
期刊：
影响因子：
--
通讯作者：
Di Niu;Zimu Liu;Baochun Li;Shuqiao Zhao
中科院分区：
文献类型：
--
作者：
Di Niu;Zimu Liu;Baochun Li;Shuqiao Zhao
对等辅助点播视频流服务是互联网上的超大规模分布式系统。自动化的需求预测和性能预测，如果实施，可以帮助容量规划和质量控制，使足够的服务器带宽总是可以提供给每个视频通道，而不会产生浪费。在本文中，我们使用时间序列分析技术来自动预测在线人口，同行上传和服务器带宽需求，在每个视频通道，基于学习的人为因素和系统动力学从在线测量。建议的机制进行评估，从商业互联网视频点播系统收集的大型数据集。
Peer-assisted on-demand video streaming services are extremely large-scale distributed systems on the Internet. Automated demand forecast and performance prediction, if implemented, can help with capacity planning and quality control so that sufficient server bandwidth can always be supplied to each video channel without incurring wastage. In this paper, we use time-series analysis techniques to automatically predict the online population, the peer upload and the server bandwidth demand in each video channel, based on the learning of both human factors and system dynamics from online measurements. The proposed mechanisms are evaluated on a large dataset collected from a commercial Internet video-on-demand system.