中国邮电高校学报(英文) ›› 2020, Vol. 27 ›› Issue (6): 30-41.doi: 10.19682/j.cnki.1005-8885.2020.0044

• • 上一篇    下一篇

Cloud security situation prediction method based on grey wolf optimization and BP neural network

赵国生 刘冬梅 王健   

  1. 1. 哈尔滨师范大学
    2. 哈尔滨理工大学
  • 收稿日期:2019-06-11 修回日期:2020-11-28 出版日期:2020-12-31 发布日期:2020-12-31
  • 通讯作者: 刘冬梅 E-mail:meiliumeidong@163.com
  • 基金资助:
    国家自然科学基金;黑龙江自然科学基金项目;哈尔滨市科技创新人才研究专项资金

Cloud security situation prediction method based on grey wolf optimization and BP neural network

Zhao Guosheng, Liu Dongmei, Wang Jian   

  • Received:2019-06-11 Revised:2020-11-28 Online:2020-12-31 Published:2020-12-31
  • Supported by:
    National Natural Science Foundation of China

摘要:

Aiming at the accuracy and error correction of cloud security situation prediction, a cloud security situation
prediction method based on grey wolf optimization (GWO) and back propagation (BP) neural network is proposed. Firstly, the adaptive disturbance convergence factor is used to improve the GWO algorithm, so as to improve the convergence speed and accuracy of the algorithm. The Chebyshev chaotic mapping is introduced into the position update formula of GWO algorithm, which is used to select the features of the cloud security situation prediction data and optimize the parameters of the BP neural network prediction model to minimize the prediction output error. Then, the initial weights and thresholds of BP neural network are modified by the improved GWO algorithm to increase the learning efficiency and accuracy of BP neural network. Finally, the real data sets of Tencent cloud platform are predicted. The simulation results show that the proposed method has lower mean square error (MSE) and mean absolute error (MAE) compared with BP neural network, BP neural network based on genetic algorithm (GA-BP), BP neural network based on particle swarm optimization (PSO-BP) and BP neural network based on GWO algorithm (GWO-BP). The proposed method has better stability, robustness and prediction accuracy.

关键词: cloud security, situation prediction, grey wolf optimization, feature selection

Abstract:

Aiming at the accuracy and error correction of cloud security situation prediction, a cloud security situation
prediction method based on grey wolf optimization (GWO) and back propagation (BP) neural network is proposed. Firstly, the adaptive disturbance convergence factor is used to improve the GWO algorithm, so as to improve the convergence speed and accuracy of the algorithm. The Chebyshev chaotic mapping is introduced into the position update formula of GWO algorithm, which is used to select the features of the cloud security situation prediction data and optimize the parameters of the BP neural network prediction model to minimize the prediction output error. Then, the initial weights and thresholds of BP neural network are modified by the improved GWO algorithm to increase the learning efficiency and accuracy of BP neural network. Finally, the real data sets of Tencent cloud platform are predicted. The simulation results show that the proposed method has lower mean square error (MSE) and mean absolute error (MAE) compared with BP neural network, BP neural network based on genetic algorithm (GA-BP), BP neural network based on particle swarm optimization (PSO-BP) and BP neural network based on GWO algorithm (GWO-BP). The proposed method has better stability, robustness and prediction accuracy.

Key words: cloud security, situation prediction, grey wolf optimization, feature selection

中图分类号: