摘要
针对大规模移动学习应用背景下流媒体服务器集群资源分配过量或不均的问题,提出了一种面向移动学习系统的多版本视频点播流媒体服务器集群资源分配方法。该方法通过用户历史点播行为日志分析,挖掘在不同终端环境下用户点播行为的特征和规律,在此基础之上,采用排队论理论进行多版本视频点播中流媒体服务器集群资源分配建模,并通过实时预测用户请求到达率的变化情况,动态调整资源的分配,从而实现了集群资源的动态配置。实验结果表明,所提方法的平均服务拒绝率和资源利用率分别在1%和80%左右,既保证了用户体验满意度,又降低了系统服务成本。
A resource allocation method for clusters of streaming media servers in multi-version VoD is proposed to solve the problem of the inappropriate resources allocation for clusters of streaming media servers in large-scale mobile learning（m-learning）system.The method analyzes user＇s historical learning logs and mines user＇s behavior characteristics,and then it utilizes the queueing theory to establish a resource allocation model for the cluster of streaming media servers.The method uses the model to predict the user arrival rate in real-time and then allocates appropriate resources dynamically.Simulation results show the correctness and efficiency of the proposed method.The average service rejection rate and average resource utilization rate are around 1% and 80% respectively.The proposed method can ensure the user experience satisfaction and reduce service cost.
出处
《西安交通大学学报》
EI
CAS
CSCD
北大核心
2016年第6期30-35,共6页
Journal of Xi'an Jiaotong University
基金
国家自然科学基金资助项目(61472317
61532015)
教育部创新团队发展计划资助项目(IRT13035)
陕西省重点实验室资助项目(2013SZS05-Z01)
