基于BBO-ELM方法的网络视频流量预测仿真研究  

Research on network video traffic prediction based on BBO-ELM method

作　　者：刘科 李军[1] Liu Ke;Li Jun(School of Automation ＆ Electrical Engineering,Lanzhou Jiaotong University,Lanzhou 730070,Chin)

机构地区：[1]兰州交通大学自动化与电气工程学院,兰州730070

出　　处：《计算机应用研究》2018年第6期1728-1732,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(51467008)

摘　　要：针对在互联网络服务中,进一步提升网络视频流量预测的精度以优化网络资源配置和满足用户需求的问题进行了研究,并对如何自适应选取网络视频流量时间序列中有效且必需的历史信息进行了探索,提出一种基于生物地理学优化算法优化极限学习机的BBO-ELM预测模型。在ELM预测模型的基础上,将BBO优化算法用于ELM的网络输入变量、隐含层节点的配置及参数、Tikhonov正则化参数的优化选取。为验证所提出方法的有效性,将BBO-ELM方法应用于真实网络视频流量预测实例中,在同等条件下,与现有方法进行了比较。仿真实验结果表明,该方法能有效地改善预测精度,显示出其有效性及应用潜力。In order to improve the accuracy of network video traffic prediction to optimize the allocation of network resources and meet the needs of users in Internet services,this paper studied how to adaptively select the effective and necessary historical information of network video traffic time series,then proposed a BBO-ELM prediction model,which based on biogeography-based optimization algorithm optimized extreme learning machine. BBO-ELM prediction model used BBO algorithm to optimize the set of input variables,the configuration and the parameters of hidden-layer nodes as well as Tikhonov＇s regularization factor on the basis of ELM. This paper applied BBO-ELM method to predict real network video traffic,and compared it with other methods under the same conditions to verify its effectiveness. Simulation experiments confirm that the proposed method provides superior prediction performance and shows good application potential.

关 键 词：生物地理学优化算法 极限学习机 网络视频流量 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]