Security Resource Allocation Method for Internet of Things Based on Reinforcement Learning

doi:10.3969/j.issn.1671-1122.2022.06.005

Abstract

Abstract:

As a decentralized computing structure, fog computing is applied in the Internet of things, and its inherent broadcast characteristics will make the network communication system to confront serious security threats. At the same time, in the dynamically changing fog Internet of things environment, the rational allocation of wireless resources is crucial to reduce the delay of communication services. Under the premise of the existence of untrusted nodes, this paper studies the security resource allocation problem of fog Internet of things. Based on the assumption that fog node receivers have simultaneous co-frequency full-duplex self-interference cancellation technology, a new method with physical layer security characteristics is proposed. It is an intelligent allocation method for radio resources in the fog layer. By constructing a deep reinforcement learning neural network and designing reasonable parameters such as state, action and reward, the method realizes the rapid upload of fog IoT perception data under the condition of security and confidentiality protection. The experimental results show that the method has a faster convergence speed and is significantly better than the comparison methods in performance.

Key words: Internet of things, reinforcement learning, resource allocation, physical layer security, secure communication

CLC Number:

TP309

ZHAO Hong, LI Shan, ZUO Peiliang, WEI Zhanzhen. Security Resource Allocation Method for Internet of Things Based on Reinforcement Learning[J]. Netinfo Security, 2022, 22(6): 44-52.

Figures/Tables 7

References 29

[1]	OMONI B, HUSSAIN R, JAVED M A, et al. Fog/Edge Computing-Based IoT(FECIoT): Architecture, Applications, and Research Issues[J]. IEEE Internet of Things Journal, 2019, 6(3): 4118-4149. doi: 10.1109/JIOT.2018.2875544 URL
[2]	GUPTA S, GARG R, GUPTA N, et al. Energy-Effcient Dynamic Homomorphic Security Scheme for Fog Computing in IoT Networks[J]. Journal of Information Security and Applications, 2021, 58: 1-8.
[3]	TARIQ N, ASIM M, AL-OBEIDAT F, et al. The Security of Big Data in Fog-Enabled IoT Applications Including Blockchain: A Survey[J]. Sensors, 2019, 19(8): 1788-1821. doi: 10.3390/s19081788 URL
[4]	SADIQUE K M, RAHMANI R, JOHANNESSON P. Fog Computing for Trust in the Internet of Things(IoT): A Systematic Literature Review[C]// IEEE. 2020 International Conference on Computer Science, Engineering and Applications(ICCSEA). New York:IEEE, 2020: 1-6.
[5]	FERRETTI L, MARCHETTI M, COLAJANNI M. Fog-Based Secure Communications for Low-Power IoT Devices[J]. ACM Transactions on Internet Technology, 2019, 19(2): 1-21.
[6]	AMOR A B, ABID M, MEDDEB A. A Secure Fog-Based Communication Scheme[C]// IEEE. 2017 International Conference on Internet of Things, Embedded Systems and Communications(IINTEC). New York:IEEE, 2017: 146-151.
[7]	WU Yongpeng, KHISTI A, XIAO Chengshan, et al. A Survey of Physical Layer Security Techniques for 5G Wireless Networks and Challenges Ahead[J]. IEEE Journal on Selected Areas in Communications, 2018, 36(4): 679-695. doi: 10.1109/JSAC.2018.2825560 URL
[8]	ZOU Yulong, ZHU Jia, WANG Xianbin, et al. A Survey on Wireless Security: Technical Challenges, Recent Advances, and Future Trends[J]. Proceedings of the IEEE, 2016, 104(9): 1727-1765. doi: 10.1109/JPROC.2016.2558521 URL
[9]	HADDAD S, OZGUR A, TELATAR E. Can Full-Duplex More Than Double the Capacity of Wireless Networks[C]// IEEE. 2017 IEEE International Symposium on Information Theory(ISIT). New York:IEEE, 2017: 963-967.
[10]	LEI Hongjiang, YANG Zixuan, PARK K H, et al. Secrecy Outage Analysis for Cooperative NOMA Systems with Relay Selection Schemes[J]. IEEE Transactions on Communications, 2019, 67(9): 6282-6298. doi: 10.1109/TCOMM.2019.2916070 URL
[11]	WANG Zhenling, PENG Zhangyou. Secrecy Performance Analysis of Relay Selection in Cooperative NOMA Systems[J]. IEEE Access, 2019, 7: 86274-86287. doi: 10.1109/ACCESS.2019.2925380
[12]	GOMEZ G, MARTIN-VEGA F J, LOPEZ-MARTINEZ F J, et al. Physical Layer Security in Uplink NOMA Multi-Antenna Systems with Randomly Distributed Eavesdroppers[EB/OL]. (2017-09-14) [2022-01-13]. https://arxiv.org/abs/1709.04693.
[13]	FENG Youhong, YAN Shihao, YANG Zhen, et al. User and Relay Selection with Artificial Noise to Enhance Physical Layer Security[EB/OL]. (2017-12-06) [2021-01-25]. https://arxiv.org/abs/1712.02104v2.
[14]	LV Lu, DING Zhiguo, NI Qiang, et al. Secure MISO-NOMA Transmission with Artificial Noise[J]. IEEE Transactions on Vehicular Technology, 2018, 67(7): 6700-6705. doi: 10.1109/TVT.2018.2811733 URL
[15]	YAN Shihao, ZHOU Xiangyun, YANG Nan, et al. Secret Channel Training to Enhance Physical Layer Security with a Full-Duplex Receiver[J]. IEEE Transactions on Information Forensics and Security, 2018, 13(11): 2788-2800. doi: 10.1109/TIFS.2018.2834301 URL
[16]	SOHRABI R, ZHU Qiping, HUA Yingbo. Secrecy Analyses of a Full-Duplex MIMOME Network[J]. IEEE Transactions on Signal Processing, 2019, 67(23): 5968-5982. doi: 10.1109/TSP.2019.2949501 URL
[17]	MOBASHERI M, KIM Y, KIM W. Toward Developing Fog Decision Making on the Transmission Rate of Various IoT Devices Based on Reinforcement Learning[J]. IEEE Internet of Things Magazine, 2020, 3: 38-42.
[18]	FAN Qiang, ANSARI N. Towards Workload Balancing in Fog Computing Empowered IoT[J]. IEEE Transactions on Network Science& Engineering, 2020, 7: 253-262.
[19]	LIU Mengyu, LIU Yuan. Price-Based Distributed Offloading for Mobile-Edge Computing with Computation Capacity Constraints[J]. IEEE Wireless Communications Letters, 2018, 7(3): 420-423. doi: 10.1109/LWC.2017.2780128 URL
[20]	XI Linhan, WANG Ying, WANG Yang, et al. Deep Reinforcement Learning-Based Service-Oriented Resource Allocation in Smart Grids[J]. IEEE Access, 2021, 9: 77637-77648. doi: 10.1109/ACCESS.2021.3082259 URL
[21]	WEI Yifei, YU F R, SONG Mei, et al. Joint Optimization of Caching, Computing, and Radio Resources for Fog-Enabled IoT Using Natural Actor-Critic Deep Reinforcement Learning[J]. IEEE Internet of Things Journal, 2019, 6(2): 2061-2073. doi: 10.1109/JIOT.2018.2878435
[22]	WYNER A D. The Wire-Tap Channel[J]. Bell System Technical Journal, 1975, 54: 1355-1387. doi: 10.1002/j.1538-7305.1975.tb02040.x URL
[23]	LI Wei, GHOGHO M, CHEN Bin, et al. Secure Communication via Sending Artificial Noise by the Receiver: Outage Secrecy Capacity/Region Analysis[J]. IEEE Communications Letters, 2012, 16(10): 1628-1631. doi: 10.1109/LCOMM.2012.081612.121344 URL
[24]	CHEN Xing, LIU Guizhong. Energy-Efficient Task Offloading and Resource Allocation via Deep Reinforcement Learning for Augmented Reality in Mobile Edge Networks[J]. IEEE Internet of Things Journal, 2021, 8(13): 10843-10856. doi: 10.1109/JIOT.2021.3050804 URL
[25]	GOUDARZI M, WU Hanming, PALANISWAMI M S, et al. An Application Placement Technique for Concurrent IoT Applications in Edge and Fog Computing Environments[J]. IEEE Transactions on Mobile Computing, 2021, 20(4): 1298-1311. doi: 10.1109/TMC.2020.2967041 URL
[26]	ZUO Peiliang, WANG Chen, YAO Ze, et al. An Intelligent Routing Algorithm for LEO Satellites Based on Deep Reinforcement Learning[C]// IEEE. IEEE 94nd Vehicular Technology Conference(VTC2021-Fall). New York:IEEE, 2021: 1-5.
[27]	YU Yiding, WANG Taotao, LIEW S C. Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks[J]. IEEE Journal on Selected Areas in Communications, 2019, 37: 1277-1290. doi: 10.1109/JSAC.2019.2904329
[28]	GU Bo, ZHANG Xu, LIN Ziqi, et al. Deep Multi-Agent Reinforcement Learning-Based Resource Allocation for Internet of Controllable Things[J]. IEEE Internet of Things Journal, 2021, 8: 3066-3074. doi: 10.1109/JIOT.2020.3023111 URL
[29]	LANGE S, RIEDMILLER M. Deep Auto-Encoder Neural Networks in Reinforcement Learning[C]// IEEE. International Joint Conference on Neural Networks(IJCNN). New York:IEEE, 2010: 1-8.

参数名称	值
雾节点$k$数量	2个
用户$u$数量	5个
潜在的通信链路数量	10条
信道带宽B	1 MHz
信噪比${{\gamma }_{u,k}}$	5~50 dB
信道增益${{g}_{u,e}}$	-80~ -100 dB
信道增益${{g}_{k,e}}$	-80~ -100 dB
用户发送功率${{p}_{u}}$	10 mw
雾节点发送功率${{p}_{k}}$	15~35 mw

参数名称	值
探索概率$\varepsilon $	0.9~0.005
$\varepsilon $衰减速率	0.995/0.01
学习率$\alpha $	0.001
折扣因子$\gamma $	0.9
经验池大小	2000
小批次容量	32