基于区块链与深度学习的空间分集协作频谱感知系统

doi:10.11959/j.issn.1000-0801.2023193

摘要/Abstract

摘要：

协作频谱感知是认知无线电中的关键技术。针对协作频谱感知中存在的安全性、隐私性、激励性和隐藏终端等问题，提出了一种运行在智能合约上的数据驱动的智能化空间分集的协作频谱感知系统。具体地，利用区块链的去中心化、数据难以篡改等特性，设计了一种激励性的协作频谱感知系统，并采用深度学习的方法来识别系统中的恶意用户。此外，针对如何更为高效地在该系统中招募感知节点以达到较高的感知准确率，设计了基于性能权重和空间分集的硬判决协作频谱感知融合算法。实验结果表明，所提算法在安全性、隐私性、激励性、感知准确率方面优于传统的协作频谱感知算法。

关键词: 协作频谱感知, 认知无线电, 区块链, 智能合约, 机器学习

Abstract:

Cooperative spectrum sensing is a key technology in cognitive radio.A data-driven intelligent cooperative spectrum sensing system was proposed with spatial diversity running on a smart contract to address issues of security, privacy, incentive and hidden terminals in cooperative spectrum sensing.Specifically, a motivated spectrum sensing system was designed by taking advantage of the decentralization of blockchain technology and the immutability of data.Secondly, a deep learning-based approach was proposed to identify malicious users in the system.In addition, to achieve higher accuracy in recruiting sensing nodes more efficiently in the system, a hard decision cooperative spectrum sensing fusion algorithm based on performance weights and spatial diversity was designed.The experimental results indicate that the proposed solution outperforms traditional cooperative spectrum sensing algorithms in terms of security, privacy, motivation, and sensing accuracy.

Key words: cooperative spectrum sensing, cognitive radio, blockchain, smart contract, machine learning

中图分类号:

TP393

肖仲杉, 王春琦, 冯大权. 基于区块链与深度学习的空间分集协作频谱感知系统[J]. 电信科学, 2023, 39(10): 49-63.

Zhongshan XIAO, Chunqi WANG, Daquan FENG. A spatial diversity cooperative spectrum sensing system based on blockchain and deep learning[J]. Telecommunications Science, 2023, 39(10): 49-63.

图/表 18

图1

图2

表1

图3

表2

图4

图5

图6

图7

图8

图9

图10

表3

图11

图12

图13

图14

图15

参考文献 20

[1]	Cisco. Cisco visual networking index:global mobile data traffic forecast update,2017–2022[R].20197.
[2]	GAO A , DU C Y , NG S X ,et al. A cooperative spectrum sensing with multi-agent reinforcement learning approach in cognitive radio networks[J]. IEEE Communications Letters, 2021,25(8): 2604-2608.
[3]	SHI Z J , GAO W , ZHANG S W ,et al. Machine learning-enabled cooperative spectrum sensing for non-orthogonal multiple access[J]. IEEE Transactions on Wireless Communications, 2020,19(9): 5692-5702.
[4]	JANU D , SINGH K , KUMAR S . Machine learning for cooperative spectrum sensing and sharing:a survey[J]. Transactions on Emerging Telecommunications Technologies, 2022,33(1): 43-52.
[5]	王晴天, 刘洋, 刘海涛 ,等. 面向 6G 的网络智能化研究[J]. 电信科学, 2022,38(9): 151-160.
	WANG Q T , LIU Y , LIU H T ,et al. Research on network intelligence for 6G[J]. Telecommunications Science, 2022,38(9): 151-160.
[6]	Federal Communication Commission. Spectrum policy task force report[R]. 2002.
[7]	PANDIT S , SINGH G . An overview of spectrum sharing techniques in cognitive radio communication system[J]. Wireless Networks, 2017,23(2): 497-518.
[8]	DENG Q Y , LI Z T , CHEN J B ,et al. Dynamic spectrum sharing for hybrid access in OFDMA-based cognitive femtocell networks[J]. IEEE Transactions on Vehicular Technology, 2018,67(11): 10830-10840.
[9]	SARIKHANI R , KEYNIA F . Cooperative spectrum sensing meets machine learning:deep reinforcement learning approach[J]. IEEE Communications Letters, 2020,24(7): 1459-1462.
[10]	JALIL S Q , CHALUP S , REHMANI M H . Cognitive radio spectrum sensing and prediction using deep reinforcement learning[C]// Proceedings of 2021 International Joint Conference on Neural Networks (IJCNN). Piscataway:IEEE Press, 2021: 1-8.
[11]	LIU C H , TSAI H C . Traffic management for heterogeneous networks with opportunistic unlicensed spectrum sharing[J]. IEEE Transactions on Wireless Communications, 2017,16(9): 5717-5731.
[12]	ZHANG Y W , ZHANG S C , WANG Y H ,et al. Riemannian mean shift-based data fusion scheme for multi-antenna cooperative spectrum sensing[J]. IEEE Transactions on Cognitive Communications and Networking, 2022,8(1): 47-56.
[13]	CHEN Z B , XU Y Q , WANG H B ,et al. Deep STFT-CNN for spectrum sensing in cognitive radio[J]. IEEE Communications Letters, 2021,25(3): 864-868.
[14]	LEE W , KIM M , CHO D H . Deep cooperative sensing:cooperative spectrum sensing based on convolutional neural networks[J]. IEEE Transactions on Vehicular Technology, 2019,68(3): 3005-3009.
[15]	LIU C , WANG J , LIU X M ,et al. Deep CM-CNN for spectrum sensing in cognitive radio[J]. IEEE Journal on Selected Areas in Communications, 2019,37(10): 2306-2321.
[16]	季薇, 李炳星, 郑宝玉 . 基于信誉与共识的分布式智能入侵防御方案[J]. 系统工程与电子技术, 2018,40(3): 665-670.
	JI W , LI B X , ZHENG B Y . Distributed intelligent intrusion prevention scheme based on reputation and consensus[J]. Systems Engineering and Electronics, 2018,40(3): 665-670.
[17]	张孟伯, 王伦文, 冯彦卿 . 基于强化学习和共识融合的分布式协作频谱感知方法[J]. 系统工程与电子技术, 2019,41(3): 486-492.
	ZHANG M B , WANG L W , FENG Y Q . Distributed cooperative spectrum sensing method based on reinforcement learning and consensus fusion[J]. Systems Engineering and Electronics, 2019,41(3): 486-492.
[18]	苗成林, 李彤, 吕军 ,等. 基于 Dempster-Shafer 证据理论与抗频谱感知数据篡改攻击的协作式频谱检测算法[J]. 兵工学报, 2017,38(12): 2406-2413.
	MIAO C L , LI T , LYU J ,et al. Cooperative spectrum sensing algorithm against spectrum sensing data falsification based on dempster-shafer evidence theory[J]. Acta Armamentarii, 2017,38(12): 2406-2413.
[19]	FENG D Q , ZHANG L , ZHANG S L ,et al. Blockchain-based secure crowdsourcing in wireless IoT[J]. Journal of Communications and Information Networks, 2022,7(1): 23-36.
[20]	PATNAIK M , PRABHU G , REBEIRO C ,et al. ProBLeSS:a proactive blockchain based spectrum sharing protocol against SSDF attacks in cognitive radio IoBT networks[J]. IEEE Networking Letters, 2020,2(2): 67-70.

变量	名称	类型
addr	地址	address
taskId	任务ID	uint
goalNum	目标招募人数	uint
currentNum	当前招募的人数	uint
deposit	押金	uint
channelNum	需检测的信道数	uint
award	奖励	uint
notice	公告	string
sensingData	感知数据	string
taskEnd	任务结束时间	uint
resultData	感知融合后的结果	string

用户	用户类别	地址	频段数	押金	奖励	感知数据	招募数量
Admin1	频谱管理者	0x78731···cabaB	1	2ether	6ether	\	3
User1	协作频谱感知用户	0x5B38D···eddC4	1	\	\	1	\
User2	协作频谱感知用户	0xAb848···35cb2	1	\	\	0	\
User3	协作频谱感知用户	0x4B209···C02db	1	\	\	1	\

对比项	随机森林	逻辑回归	SVM	LightGBM	XGBoost	DNN
准确率	0.777	0.645	0.639	0.760	0.731	0.787
AUC	0.835	0.713	0.703	0.825	0.800	0.860
F1-score	0.759	0.652	0.651	0.750	0.722	0.765
召回率	0.698	0.662	0.671	0.715	0.700	0.690