基于蚁群算法优化BP神经网络的政务云网络态势预测研究  

Research on government cloud network situation prediction based on ant colony algorithm optimized BP neural network

作　　者：王岩雪 孙大跃[1] WANG Yanxue;SUN Dayue(School of Information Engineering,Chang’an University,Xi’an 710064,China)

机构地区：[1]长安大学信息工程学院,陕西西安710064

出　　处：《现代电子技术》2020年第21期72-75,共4页Modern Electronics Technique

基　　金：国家自然科学基金(61572083)。

摘　　要：针对常规BP神经网络预测模型存在的预测精度低、收敛速度慢等问题,给出一种蚁群优化BP神经网络预测模型,用于政务云的网络安全态势预测。同时,对蚁群算法的信息素更新规则进行改进,并将改进后的蚁群算法应用于BP神经网络权值和阈值的优化,得到BP神经网络预测模型的最优权值和阈值,并将最优权值和阈值用于BP神经网络训练和预测。实验仿真结果表明,与传统BP神经网络安全预测模型相比,采用优化后的模型进行网络安全态势预测时,其收敛速度和预测精度都得到了明显的提高。In view of the low prediction accuracy and slow convergence speed of the conventional BP(back propagation)neural network prediction model,an ant colony algorithm optimized BP neural network prediction model is proposed for the network security situation prediction of government cloud.Meanwhile,the pheromone update rule of ant colony algorithm is improved,and the improved ant colony algorithm is used to optimize the weight and threshold value of BP neural network to get the optimal weight and threshold value of BP neural network prediction model,and the optimal weight and threshold value are used for the BP neural network training and prediction.The results of simulation experiment show that,in comparison with the traditional BP neural network security prediction model,the convergence speed and prediction accuracy of the network security situation prediction of the optimized model are improved significantly.

关 键 词：政务云 主动防御 BP神经网络 蚁群算法 态势预测 预测精度 

分 类 号：TN711-34[电子电信—电路与系统]