基于改进RNN的网络异常流量检测研究

Research on network abnormal traffic detection based on improved RNN

随着计算机和网络的发展,人们的生活已经逐渐离不开网络了,网络的出现为人们的生活、工作和出行带来了极大的便利。在这种情况下,检测网络流量,实时侦探出网络流量异常变得十分重要。文章针对传统网络异常流量检测方法的缺陷即无法自动提取特征和无法体现时序性的问题,设计了一个基于改进RNN的网络异常流量检测模型。该模型可以较好地预测网络流量并通过与真实流量做对比进行网络流量预警。与历史传统方法相比,该模型减轻了人工量并且较少了网络参数,减少了训练时间。

With the development of computer and network,people’s life has been gradually inseparable from the network.The emergence of the network has brought great convenience to people’s life,work and travel.In this case,it is very important to detect network traffic and detect network traffic anomalies in real time.In this paper,aiming at the defects of traditional network abnormal traffic detection methods,that is,unable to extract features automatically and can not reflect the timing,a network abnormal traffic detection model based on improved RNN is designed.This model can better predict the network traffic and carry on the network traffic early warning by comparing with the real traffic.Compared with the traditional historical methods,this model reduces the amount of labor and network parameters,and reduces the training time.