摘要
对等网络技术引起了广泛关注,其典型的应用有文件共享、即时通信等。为了更好地合理使用、规划P2P网络资源,建立P2P流量识别模型具有十分重要的理论意义和现实价值。提出了一种基于小波支持向量机相结合的P2P流量识别模型,将小波分析中多尺度的学习方法和SVM的优点结合起来,通过小波分析与SVM方法紧致结合,引入满足小波构架和Mercer定理的小波基函数来构造SVM的核函数,建立小波支持向量机的P2P识别算法。实验结果表明该算法能够有效地提高P2P网络流量识别的精度。
Recently,there has been a growing interest in the potential use of peer to peer computing in many applications such as file sharing,instant communication.Therefore,to realize their potential,there is a need of a P2P traffic identification algorithm that facilities the deployment of a network traffic that is optimized in terms of network bandwith.Focuses on developing a novel P2P traffic prediction using wavelet support vector machine.Through the wavelet analysis combined with the SVM method of compact,introduced to meet the wavelet framework and Mercer theorem to construct the wavelet function SVM kernel function,wavelet support vector machines to establish P2P identification algorithm.Experimental results show that the algorithm can effectively improve the accuracy of P2P network traffic identification.
出处
《计算机技术与发展》
2010年第10期107-110,114,共5页
Computer Technology and Development
