摘要
针对网络安全态势预测问题,提出了一种预测方法。该方法采用协方差矩阵自适应进化策略(CMA-ES)算法来优化径向基神经网络(RBF)预测模型中的参数,使得RBF预测模型具备更好的泛化能力,可以快速的找出复杂时间序列中的规律。仿真实验结果表明,采用CMA-ES优化的RBF预测模型能够准确预测出一段时间内的网络安全态势值,预测精度高于传统预测手段。
A method for network security situation prediction is proposed, where the covariance matrix adaptation evolution strategy algorithm （CMA-ES） is used to optimize the parameters of the radial basis function neural network forecasting model （RBF）, which makes the forecasting model have superior ability, and can quickly find out the rules of the complex time series. The simulations results show that the proposed method can accurately predict the network security situation, and has better prediction accuracy than traditional prediction methods.
出处
《哈尔滨理工大学学报》
CAS
北大核心
2017年第2期140-144,共5页
Journal of Harbin University of Science and Technology
基金
吉林省教育厅科学技术研究项目(吉教科合字[2014]第145号
[2016]第344号)
海南省自然科学基金面上项目(617120
617121)
关键词
网络安全态势预测
CMA-ES优化算法
RBF神经网络
时间序列预测
network security situation prediction
covariance matrix adaptation evolution strategy algorithm
Radial basis function neural network
time series prediction
