Network security assessment based on hidden Markov and artificial immunization in new power systems

doi:10.3969/j.issn.1000-5641.2023.05.015

Abstract

Abstract:

Advanced metering infrastructure is an important component in the construction of new power systems; however, advanced measurement systems rely on network information infrastructures and present major security issues. This study evaluates the network security posture of advanced metering systems by combining a hidden Markov model with an artificial immunity algorithm. First, a counting algorithm is used to obtain the security observation data in the power network. Subsequently, the Markov model is used to describe the change in the network security state, whereby the artificial immunity algorithm calculates the transfer probability matrix between different states. The state transfer matrix is then modified based on the state assessment error. Upon calculating the probability of being at different security states at different times and combining it with the risk loss vector, the final value of safety posture is obtained. The experiments demonstrate that the method proposed in this study has a good assessment effect and can capture the safety defects in the system more accurately, ensuring the safe operation of the advanced measurement system by accurately identifying the relevant safety defects in the system for a safe, smooth, and reliable operation of the new grid environment.

Key words: new power system, advanced metering infrastructure, situation assessment, network security, hidden Markov model (HMM), artificial immunization

CLC Number:

TP391

Zhi XU, Jun CHEN, Zhiyong ZHANG, Junling WAN, Peisen YUAN. Network security assessment based on hidden Markov and artificial immunization in new power systems[J]. Journal of East China Normal University(Natural Science), 2023, 2023(5): 182-192.

Figures/Tables 11

Table 1

Fig.1

Table 2

Table 3

Table 4

Fig.2

Table 5

Fig.3

Fig.4

Fig.5

Fig.6

References 30

1	胡厚鹏, 肖艳红, 吴才远, 等.. 计及多端互联通信的智能电网AMI新型密钥管理方案. 西南师范大学学报(自然科学版), 2023, 48 (3): 9- 16.
2	陈伟雄, 杨晓晨, 春增军, 等.. 电力企业网络安全威胁情报管理体系的研究与实践. 电信科学, 2022, 38 (7): 184- 189.
3	金志刚, 刘凯, 武晓栋.. 智能电网AMI领域IDS研究综述. 信息网络安全, 2023, 23 (1): 1- 8.
4	WANG S, CHEN H, ZHAO Q, et al.. Preserving scheme for user’s confidential information in smart grid based on digital watermark and asymmetric encryption. Journal of Central South University, 2022, 29 (2): 726- 740.
5	周劼英, 张晓, 邵立嵩, 等.. 新型电力系统网络安全防护挑战与展望. 电力系统自动化, 2023, 47 (8): 15- 24.
6	欧家祥, 胡厚鹏, 何沛林, 等.. 基于国密算法的电网AMI数据安全防护技术. 西南师范大学学报(自然科学版), 2023, 48 (3): 17- 24.
7	赵小林, 曾冲寒, 薛静锋, 等.. 基于TOPSIS的多维网络安全度量模型研究. 北京理工大学学报, 2021, 41 (3): 311- 321.
8	王增平, 林一峰, 王彤, 等.. 电力系统继电保护与安全控制面临的挑战与应对措施. 电力系统保护与控制, 2023, 51 (6): 10- 20.
9	严康, 陆艺丹, 于宗超, 等.. 配电网用户侧异构电力物联设备安全研究综述及展望. 电力自动化设备, 2023, 43 (3): 146- 158.
10	REN J.. Network security situation assessment model based on information quality control. International Journal of Performability Engineering, 2020, 16 (4): 673- 680.
11	蒋文辉, 席禹, 于力, 等.. 基于智能电网服务器的网络安全可视化研究. 自动化与仪表, 2023, 38 (4): 6- 9.
12	肖鹏, 王柯强, 黄振林.. 基于IABC和聚类优化RBF神经网络的电力信息网络安全态势评估. 智慧电力, 2022, 50 (6): 100- 106.
13	王金恒, 单志龙, 谭汉松, 等.. 基于遗传优化PNN神经网络的网络安全态势评估. 计算机科学, 2021, 48 (6): 338- 342.
14	LIU Z, YANG C, LIU Y, et al.. A BIPMU-based network security situation assessment method for wireless network. Computer Standards & Interfaces, 2023, 83, 103661.
15	苏鹏涛, 吴贶, 陈孟婕, 等.. 基于隐马尔可夫模型的电力信息系统动态威胁定量分析. 上海理工大学学报, 2022, 44 (4): 388- 396.
16	段青青.. 基于HMM算法的英语形音匹配可视分析. 计算机应用与软件, 2021, 38 (8): 44- 50.
17	张明恒, 刘朝阳, 郭政先, 等.. 基于GM-HMM的驾驶人疲劳状态检测. 大连理工大学学报, 2021, 61 (4): 399- 407.
18	KHREICH W, GRANGER E, MIRI A, et al.. Adaptive ROC-based ensembles of HMMs applied to anomaly detection. Pattern Recognition, 2012, 45 (1): 208- 230.
19	徐佳伟, 罗倩.. 基于遗传非参数MDL-BW方法的HMM结构优化. 电子学报, 2022, 50 (11): 2765- 2772.
20	ÅRNES A, SALLHAMMAR K, HSALUM K, et al. Real-time risk assessment with network sensors and intrusion detection systems[C]// Computational Intelligence and Security: International Conference. Berlin, Heidelberg: Springer-Verlag, 2005: 388-397.
21	LI B, WU F, LIU J, et al.. Real-time scheduling of virtual power system based on the hidden Markov model. Journal of Physics: Conference Series, 2022, 2401 (1): 012023.
22	张铠翔, 姜文刚.. 基于人工免疫的渐消容积粒子滤波目标跟踪算法. 计算机应用与软件, 2022, 39 (12): 266- 271.
23	李涛, 兰小龙, 李贝贝, 等.. 内生安全支撑的新型网络体系结构与关键技术研究构想与成果展望. 工程科学与技术, 2023, 55 (2): 1- 13.
24	琚安康, 郭渊博, 李涛, 叶子维.. 基于网络通信异常识别的多步攻击检测方法. 通信学报, 2019, 40 (7): 57- 66.
25	马云珍. 网络多步攻击场景还原及预测关键技术研究 [D]. 哈尔滨: 哈尔滨工程大学, 2017.
26	席荣荣, 云晓春, 张永铮, 等.. 一种改进的网络安全态势量化评估方法. 计算机学报, 2015, 38 (4): 749- 758.
27	常利伟, 刘秀娟, 钱宇华, 等.. 基于卷积神经网络多源融合的网络安全态势感知模型. 计算机科学, 2023, 50 (5): 382- 389.
28	ÅRNES A, VALEUR F, VIGNA G, et al. Using hidden Markov models to evaluate the risks of intrusions: System architecture and model validation [C]// ZAMBONI D, KRUEGEL C. Recent Advances in Intrusion Detection: 9th International Symposium. Berlin, Heidelberg: Springer-Verlag, 2006: 145-164.
29	HASLUM K, MOE M E G, KNAPSKOG S J. Real-time intrusion prevention and security analysis of networks using HMMs [C]// 2008 33rd IEEE Conference on Local Computer Networks (LCN). IEEE, 2008: 927-934.
30	李伟明, 雷杰, 董静, 等.. 一种优化的实时网络安全风险量化方法. 计算机学报, 2009, 32 (4): 793- 804.

分类	解释
$ i $	对应安全状态的分类, 电力网络采集不到任何非安全隐患警报
$ p $	预攻击类的安全警报
$ a $	攻击入侵类的警报
$ c $	攻陷电力网络的警报

安全事件	网络安全防范措施
安全事件	$ \varnothing $	$ {D_{\rm{S}}} $	$ {D_{\rm{F}}} $	$ {D_{\rm{R}}} $
$ \varnothing $	$ I $	$ I $	$ I $	$ I $
$ {E_{\rm{P}}} $	$ P $	(1/2)P、(1/2)I	(1/2)P、(1/2)I	$ I $
${E_{\rm{A}}}$	$ A $	(1/4)I、(3/4)A	(1/2)A、(1/2)I	$ I $
$ {E_{\rm{C}}} $	$ C $	(1/4)I、(3/4)C	(1/2)C、(1/2)I	$ I $

编号	来源	开始时间	结束时间	警报数
1	获取电力网络主机的列表	09:51:36	09:52:00	31
2	开始预攻击, 寻找薄弱主机	10:08:07	10:18:10	32
3	通过寻找到的漏洞侵入系统	10:33:10	10:35:01	35
4	对控制的主机进行木马攻击	10:50:01	10:50:54	22
5	对服务器进行攻击	11:26:15	11:34:21	33754

真实/预测	正例	反例
正例	TP (真正例)	FN(假反例)
反例	FP (假正例)	TN(真反例)

算法/状态	安全状态	预攻击状态	入侵状态	攻陷状态
本文算法	10 min 前, 170 min, 180 min	10~60 min, 135 min, 150 min, 190~200 min	60~85 min, 100~190 min 主要是入侵状态	90~100 min
Xi	20 min 前, 160 min 后	20~70 min	70~160 min	/
Arnes	15 min 前	15 min 后	/	/
Haslum	安全状态和预攻击状态两种状态相互交替出现		/	/
遗传算法	几种状态下的概率值没有大和明显小的状态概率			/