为了解决单一信息源带来的网络安全状态感知误差高的问题，研究舰船通信系统5G网络多维度安全状态感知技术。构建舰船通信系统5G网络多维度安全状态感知框架，通过多源网络安全状态信息采集单元获取5G网络安全状态信息，融合处理单元利用层次量化评估方法对其作标准化等处理后，获得5G网络安全态势样本数据集，将其作为基于Att-GRU的5G网络安全状态感知模型的输入，利用鲸鱼优化算法实现模型参数的寻优，输出为5G网络安全态势预测结果，依据预测结果与实际结果的差值计算5G网络健康度，通过还原单元对预测结果作累减反归处理，获得5G网络安全态势值，并与设置阈值作对比，实现舰船通信系统5G网络的多维度安全状态感知。实验结果表明：该技术可实现5G网络安全状态感知，神经元个数为35、批处理规模为1.2时，5G网络安全状态感知模型性能最优；5G网络安全态势预测的平均适应度与最优适应度相贴近。
Research on multidimensional security state perception technology for 5G network of ship communication system, to solve the problem of high network security state perception error caused by a single information source. Construct a multidimensional security state awareness framework for the 5G network of ship communication system. Obtain the 5G network security state information through a multi-source network security state information collection unit, and standardize it using a hierarchical quantitative evaluation method by the fusion processing unit. Obtain the 5G network security state sample dataset, which is used as input for the 5G network security state awareness model based on Att GRU. Optimize the model parameters using whale optimization algorithm, The output is the 5G network security situation prediction result, and the 5G network health degree is calculated based on the difference between the prediction result and the actual result. The prediction result is processed by the reduction unit to obtain the 5G network security situation value, which is compared with the set threshold to achieve multidimensional security state perception of the 5G network in the ship communication system. The experimental results show that this technology can achieve 5G network security state awareness. When the number of neurons is 35 and the batch processing scale is 1.2, the performance of the 5G network security state awareness model is optimal; The average fitness of 5G network security situation prediction is close to the optimal fitness.
2023,45(22): 186-189 收稿日期：2023-7-4
DOI：10.3404/j.issn.1672-7649.2023.22.035
分类号：TP393
作者简介：黄福全(1977-),男,高级工程师,研究方向为电网运行管理
参考文献：
[1] 刘亚天, 呼博文, 陈茂飞, 等. 5GC安全态势感知系统研究[J]. 电信科学, 2022, 38(11): 73-85.
LIU Ya-tian, HU Bo-wen, CHEN Mao-fei, et al. Study on the 5GC security situational awareness system[J]. Telecommunications Science, 2022, 38(11): 73-85.
[2] 张红斌, 尹彦, 赵冬梅, 等. 基于威胁情报的网络安全态势感知模型[J]. 通信学报, 2021, 42(6): 182-194.
ZHANG Hong-bin, YIN Yan, ZHAO Dong-mei, et al. Network security situational awareness model based on threat intelligence[J]. Journal on Communications, 2021, 42(6): 182-194.
[3] 耿方方, 王昂. 基于量子遗传算法的网络安全态势感知研究[J]. 计算机仿真, 2021, 38(8): 348-351+491.
GENG Fang-fang, WANG Ang. Research on network security situation awareness based on quantum genetic algorithm[J]. Computer Simulation, 2021, 38(8): 348-351+491.
[4] 丁华东, 许华虎, 段然, 等. 基于贝叶斯方法的网络安全态势感知模型[J]. 计算机工程, 2020, 46(6): 130-135.
DING Hua-dong, XU Hua-hu, DUAN Ran, et al. Network security situation awareness model based on bayesian method[J]. Computer Engineering, 2020, 46(6): 130-135.
[5] 何春蓉, 朱江. 基于注意力机制的GRU神经网络安全态势预测方法[J]. 系统工程与电子技术, 2021, 43(1): 258-266.
HE Chun-rong, ZHU Jiang. Security situation prediction method of GRU neural network based on attention mechanism[J]. Systems Engineering and Electronics, 2021, 43(1): 258-266.
