文献类型：期刊文献

中文题名：基于ACO-LSSVM的网络流量预测

英文题名：Network traffic prediction based on LSSVM optimized by ACO

作者：田海梅[1];黄楠[2]

第一作者：田海梅

机构：[1]金陵科技学院信息技术学院;[2]新乡学院计算机与信息工程学院

第一机构：金陵科技学院信息技术学院,南京211169

年份：2014

期号：1

起止页码：91-95

中文期刊名：计算机工程与应用

外文期刊名：Computer Engineering and Applications

收录：CSTPCD;;CSCD:【CSCD2013_2014】；

基金：金陵科技学院博士启动基金(No.JIT-B-01);金陵科技学院自然科学基金(No.208.40410826)

语种：中文

中文关键词：网络流量;蚁群优化算法;最小二乘支持向量机;预测;Least;Square;Support;Vector;Machine(LSSVM)

外文关键词：network traffic;Ant Colony Optimization（ACO）algorithm;prediction

摘要：为了提高了网络流量的预测精度,提出一种蚁群算法(ACO)优化最小二乘支持向量机(LSSVM)参数的网络流量预测算法(ACO-LSSVM)。将LSSVM算法参数作为蚂蚁的位置向量,采用动态随机抽取的方法来确定目标个体引导蚁群进行全局搜索,并在最优蚂蚁邻域内进行小步长局部搜索,找到算法的最优参数,建立了基于ACO-LSSVM的网络流量预测模型。仿真结果表明,相对其他网络流量预测算法,ACO-LSSVM算法提高了网络流量预测精度,更能准确地描述网络流量变化规律。
In order to improve the prediction accuracy of network traffic, this paper proposes a network traffic prediction method based on Ant Colony Optimization（ACO）algorithm and Least Square Support Vector Machine（LSSVM）. In this method, the parameters of LSSVM model are considered as the position vector of ants. Target individuals which lead the ant colony to do global rapid search are determined by dynamic and stochastic extraction, and the optimal ant of this generation searches in small step nearly, lastly, the optimal parameter value is obtained by ACO. The simulation results show that, compared with other network traffic prediction model, the proposed method improves prediction accuracy and can more accurately describe the change rule of network flow.