基于高阶图卷积自编码器的网络流量预测
投稿时间:2020-06-16  修订日期:2020-07-21  点此下载全文
引用本文:
摘要点击次数: 42
全文下载次数: 0
作者单位E-mail
崔兆阳 广州供电局有限公司 luntan2019@126.com 
李昭桦 中国能源建设集团广东省电力设计研究院有限公司 WenjingZ97@163.com 
基金项目:广州供电局基金项目:基于SDN控制器的数据网可视化流量调度技术研究及应用(基金编号:GZHKJXM20170117)
中文摘要:网络流量预测是有效保障用户QoS措施之一。当前深度学习为基础的网络算法预测中没有充分利用网络拓扑信息。为此,提出了基于高阶图卷积自编码器的网络流量预测模型。该流量预测模型基于软件定义网络(SDN)架构,利用高阶图卷积网络(GCN)获取网络拓扑中的多跳邻域之间的流量相互影响关系,采用门控递归单元(GRU)获取网络的时间相关性信息,利用自编码模型来实现无监督学习和预测。在Abilene网络上采用真实数据进行了仿真对比分析试验,结果表明,提出的方法在网络流量检测方面的MAPE值为41.56%,低于其它深度学习的方法,同时预测准确率方面也达到最优。
中文关键词:流量检测  高阶图卷积  GRU自编码器  网络拥塞预测
 
NETWORK TRAFFIC PREDICTION BASED ON K-HOPS GRAPH CONVOLUTINAL AUTOENCODER
Abstract:Network traffic prediction is one of the effective way to improve user QoS. The network topology information is not fully utilized in current network algorithm prediction. In the paper, we propose a network traffic detection model based on high order graph convolutional network algorithm, and further predicts network congestion based on traffic information. The traffic prediction model utilizes the graph convolutional to capture the mix-hop effect of traffic. And the gated recurrent unit (GRU) obtains the time correlation information of the traffic in the network. The autoencoder model implements the unsupervised learning and traffic prediction. The simulation experiment is on the real data of the network Abilene. The experimental results show that the mean absolute percentage error(MAPE) value of the method in network traffic detection is 41.56%, which is lower 1.64% than DCRNN methods. At the same time, the prediction accuracy of this paper is also optimal.
keywords:network traffic detection  k-hops graph neural network  GRU autoencoder  network traffic prediction
查看全文   查看/发表评论   下载pdf阅读器