改进的Wolf一步预测的网络异常流量检测

发布时间：2018-03-03 12:48

本文选题：网络流量　切入点：混沌　出处：《科技通报》2014年02期 　论文类型：期刊论文

【摘要】：在网络预测算法中传统的预测几乎都没有考虑流量的自相似性和高斯性,仅仅利用最大Lyapunov指数进行计算机网络流量的混沌性检验,对网络流量的预测也仅仅是以计算得到的最大Lyapunov指数为前提,算法精度受限。提出一种改进的Wolf一步预测算法,对网络流量通过自相似的FGN(FGN,fractional gaussian noise)过程处理,得到替代原网络流量的新的序列,新的替代流量序列具有自相似性,从而进行预测。仿真结果准确检验了网络流量的混沌性,预测结果表明,改进的预测算法在略有缩短最大预报时间下,精度却高很多,预测的误差小于3%的点比例比原传统算法提高了20%以上。
[Abstract]:In the traditional network prediction algorithms, the self-similarity of traffic and Gao Si are hardly taken into account, and the chaos of computer network traffic is only tested by using the largest Lyapunov exponent. The prediction of network traffic is only based on the calculation of the largest Lyapunov exponent, and the accuracy of the algorithm is limited. An improved Wolf one-step prediction algorithm is proposed to process network traffic through the self-similar FGNN FGNN gaussian noiseal process. A new sequence is obtained to replace the original network traffic, and the new alternative traffic sequence has self-similarity, so it can be predicted. The simulation results verify the chaos of the network traffic accurately, and the prediction results show that, The precision of the improved prediction algorithm is much higher than that of the traditional algorithm, and the prediction error is less than 3%. The accuracy of the improved prediction algorithm is 20% higher than that of the traditional algorithm.
【作者单位】：首都经济贸易大学信息工程系;
【分类号】：TP393.06

【参考文献】