基于ADMPDE-WNN的网络安全态势预测方法

发布时间：2018-09-17 15:43

【摘要】：精确预测网络安全态势,对分析网络安全态势和趋势、调整安全策略具有重要意义。针对复杂网络系统规模变化,建立了层次化网络安全态势评估模型;在分析小波神经网络(WNN)基本原理及优缺点的基础上,将具有寻优能力强、收敛速度快的自适应局部增强微分进化算法(ADMPDE)与WNN算法相结合,提出了基于ADMPDE-WNN的态势预测方法。通过仿真实验分析,ADMPDE-WNN算法大大减小了训练误差和预测误差,提高了网络安全态势预测精度。基于ADMPDE-WNN的网络安全态势预测是一种科学、合理的预测方法,具有一定的理论意义和应用价值。
[Abstract]:It is of great significance to predict the network security situation accurately and to analyze the network security situation and trend and adjust the security policy. According to the scale change of complex network system, the hierarchical network security situation assessment model is established, based on the analysis of the basic principle, advantages and disadvantages of wavelet neural network (WNN), it will have a strong ability to find the best. An adaptive locally enhanced differential evolution algorithm (ADMPDE) with high convergence speed is combined with the WNN algorithm, and a situation prediction method based on ADMPDE-WNN is proposed. The simulation results show that the ADMPDE-WNN algorithm greatly reduces the training error and prediction error, and improves the precision of network security situation prediction. Network security situation prediction based on ADMPDE-WNN is a scientific and reasonable prediction method, which has certain theoretical significance and application value.
【作者单位】：空军工程大学防空反导学院;中国人民解放军93942部队;宝鸡石油机械有限责任公司;
【基金】：国家科技重点实验室基金项目(9140XXXXXX110)
【分类号】：TP393.08

【参考文献】