摘要
流量预测是计算机网络管理的一项关键技术,以提高网络流量预测的准确性为目标,本文提出一种粒子群优化算法和最小二乘支持向量机的网络流量预测模型。首先对网络流量历史数据进行混沌分析,重构网络流量样本集,然后采用粒子群算法优化最小二乘支持向量机对网络流量数据进行建模,最后采用仿真模拟实验对网络流量的预测结果分析。实验结果表明,其模型可以描述网络流量的变化趋势,获得高精度的网络流量预测结果,提供了一种新网络流量预测工具。
Network traffic forecasting is a key technology in computer network management. In order to improve the accuracy of network traffic forecasting, a network traffic forecasting model based on particle swarm optimization algorithm and least square support vector machine is proposed in this paper. Firstly, it analyzes the historical data of network traffic by chaotic theory, and reconstructs the network traffic sample. And then, particle swarm optimization algorithm optimizing least square support vector machine is used to model the network traffic data. Finally, the simulation results are used to test the forecasting results of network traffic. Experimental results show that the proposed model can describe the change trend of network traffic, and obtain the high accuracy of network traffic forecasting results, which provides a new tool for network traffic modeling and forecasting.
出处
《微型电脑应用》
2016年第5期27-30,共4页
Microcomputer Applications
基金
河南省科技攻关项目(132102210208)
关键词
网络流量预测
最小二乘支持向量机
粒子群优化算法
核函数参数选择
Network Traffic Forecast
Least Squares Support Vector Machine
Particle Swarm Optimization Algorithm
Kernel Function Parameter Selection