摘要
随着网络技术的发展,人们对网络服务质量提出更高的需求。对网络流量准确的建模,预测未来的网络流量,是保证网络服务质量和可靠性的重要措施。提出了一种基于Windows集群的自相似网络流量模型解决方案。该方案采用分形高斯噪声(FGN)模型并行算法,由基于Windows HPC Server的集群系统生成网络流量。详细描述了基于集群平台的系统设计和实现过程。实验结果表明,该系统能够生成大规模的具有指定Hurst系数的自相似网络流量,同时克服了单机系统及分布式系统的局限性。
With the development of network technology, people expect more and more of network service. Modeling network traffic accurately, predicting approaching network traffic are important measures to ensure the quality and reliability of network service. This paper presents a solution for self-similar traffic model based on windows cluster. In the solution, the Fractal Gaussian Noise （FGN） model is improved to a high-speed parallel algorithm. And the new parallel algorithm is applied to the distributed system, which then is deployed on the Windows HPC Cluster. The report describes the design and implementation of the cluster system in detail. Statistical results of the report suggest that the cluster system can generate large-scale self-similar network traffic with designated Hurst parameter, and overcome the limitations of the single computer and the distributed system.
出处
《计算机工程与应用》
CSCD
2012年第25期105-111,共7页
Computer Engineering and Applications
基金
天津市科技攻关项目(No.043185111-15)
天津市自然科学基金(No.06YFJMJC00300)
关键词
集群
自相似性
网络流量
cluster
self-similar
network traffic
