论文部分内容阅读
流量建模与预测对了解光通信网络变化状态具有重要意义,为了有效描述光通信网络流量的混沌性,提出一种大规模光通信网络流量的非线性建模与预测方法。首先利用相空间重构理论对光通信网络流量数据进行预处理,然后采用最小二乘支持向量机描述光通信网络流量的变化特点,并采用遗传算法选择核函数参数和惩罚参数,最后采用光通信网络流量预测实例对其性能进行实证分析,并与其它方法进行对比实验。实验结果表明,本文方法具有较高的光通信网络流量预测精度,可以描述光通信网络流量的混沌性,具有一定推广价值。
Traffic modeling and prediction are of great importance to understand the changing state of optical communication networks. In order to effectively describe the chaos of optical communication network traffic, a nonlinear modeling and prediction method for large-scale optical network traffic is proposed. Firstly, the phase space reconstruction theory is used to preprocess the traffic data in the optical communication network. Then, the least square support vector machine (SVM) is used to describe the characteristics of the traffic changes in the optical communication network. The kernel parameters and the penalty parameters are selected by genetic algorithm. Finally, The example of network traffic forecasting makes an empirical analysis of its performance and compares it with other methods. The experimental results show that the proposed method has a high prediction accuracy of optical network traffic and can describe the chaos of optical network traffic, which has a certain promotion value.