Spectrum Sensing for OFDMA Using Multicarrier Covariance Matrix Aware CNN

doi:10.12142/ZTECOM.202203008

ZTE Communications ›› 2022, Vol. 20 ›› Issue (3): 61-69.DOI: 10.12142/ZTECOM.202203008

• Research Paper • Previous Articles Next Articles

Spectrum Sensing for OFDMA Using Multicarrier Covariance Matrix Aware CNN

ZHANG Jintao¹, HE Zhenqing¹(), RUI Hua^2,³, XU Xiaojing^2,³

^1.National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China, Chengdu 611731, China
^2.ZTE Corporation, Shenzhen 518057, China
^3.State Key Laboratory of Mobile Network and Mobile Multimedia Technology, Shenzhen 518055, China

Received:2022-03-06 Online:2022-09-13 Published:2022-09-14
About author:ZHANG Jintao received his BS and MS degrees in communication engineering from the University of Electronic and Science Technology of China, in 2019 and 2022, respectively. His research interests include spectrum sensing and deep learning.|HE Zhenqing (zhengqinghe@uestc.edu.cn) received his PhD degree in communication and information system from the University of Electronic Science and Technology of China (UESTC) in 2017. From 2015 to 2016, he was a visiting PhD student with the Department of Electrical and Computer Engineering, Stevens Institute of Technology, USA. Since 2018, he has been with the National Key Laboratory of Science and Technology on Communications, UESTC, where he is currently an associate professor. His main research interests include statistical signal processing, wireless communications, and machine learning. He was a recipient of the IEEE Communications Society Heinrich Hertz Prize Paper Award in 2022.|RUI Hua received his BS, MS, and PhD degrees from Nanjing University of Aeronautics and Astronautics, China in 1999, 2002, and 2005, respectively. He currently works as a senior pre-research expert and the head of the 6G Future Wireless Lab in ZTE Corporation. He has been engaged in wireless communication product and new technology pre-research, including 3G/4G/WIFI/5G/6G network architecture and key technologies. At present, his main research direction is the 6G wireless communication technology, including new receiver research integrated with communication-sensing-computing, NB-NTN narrow-band low-orbit satellite system and key technologies, 6G network architecture and protocol standardization research, digital twin wireless network technology, network intelligence, regional block chain network, etc. He has published more than 20 invention patents and papers in related fields. He has participated in more than 10 industry technical standards and white papers including 3GPP 3G/4G/5G series standards and IEEE 802.11 series standards.|XU Xiaojing received her BS and MS degrees in communication and information system from Northeastern University, China in 2006 and 2008, respectively. At present, she works in ZTE Corporation as a senior algorithm engineer in the Algorithm Department. She has been engaged in wireless communication technology pre-research and product algorithm research. Her research interests include the 6G wireless communication physical layer technology and wireless AI technology. She has published more than 10 invention patents and papers in related fields.
Supported by:
ZTE Industry-University-Institute Cooperation Funds(HC-CN-2020120002)

Abstract

Abstract:

We consider spectrum sensing problems in the orthogonal frequency division multiplexing access (OFDMA) cognitive radio scenario, where a secondary user with multiple antennas detects several consecutive subcarriers of an entire OFDM symbol occupied by multiple primary users. Specifically, an OFDM multicarrier covariance matrix convolutional neural network (CNN)-based approach is proposed for simultaneously detecting the occupancy of all OFDM subcarriers, where the multicarrier sample covariance matrix array is specially set as the input of the CNN. The proposed approach can efficiently learn the energy information and correlation information between antennas and between subcarriers to significantly improve the spectrum sensing performance. Numerical results demonstrate that the proposed method has a substantial performance advantage over the state-of-the-art spectrum sensing methods in an OFDMA scenario under the 5G new radio network.

Key words: cognitive radio, spectrum sensing, OFDMA, deep learning, 5G new radio

ZHANG Jintao, HE Zhenqing, RUI Hua, XU Xiaojing. Spectrum Sensing for OFDMA Using Multicarrier Covariance Matrix Aware CNN[J]. ZTE Communications, 2022, 20(3): 61-69.

Figures/Tables 9

Figure 1 PUs’ occupancy on an orthogonal frequency division multiplexing (OFDM) symbol

Figure 2 OFDM multicarrier covariance matrix-CNN sensing workflow for spectrum sensing

Figure 3 OFDM multicarrier covariance matrix array and its corresponding subchannel occupancy

Table 1 Computational complexity of respective algorithms

Algorithms	Online Sensing	Offline Training
Energy detection^[5]	$O B M N$	×
Eigenvalue-based methods^[8–12]	$O B M 2 N + B M 3$	×
OMCM-CNN	$O B M 2 N + B$ + $O ∑ l = 1 D n l - 1 s l 2 n l m l 2$	$O N t N e B M 2 N + B$ + $O N t N e ∑ l = 1 D n l - 1 s l 2 n l m l 2$

Table 1 Computational complexity of respective algorithms

Algorithms	Online Sensing	Offline Training
Energy detection^[5]	$O B M N$	×
Eigenvalue-based methods^[8–12]	$O B M 2 N + B M 3$	×
OMCM-CNN	$O B M 2 N + B$ + $O ∑ l = 1 D n l - 1 s l 2 n l m l 2$	$O N t N e B M 2 N + B$ + $O N t N e ∑ l = 1 D n l - 1 s l 2 n l m l 2$

Table 2 Hyper parameters of the proposed CNN

Input: Multicarrier Covariance Matrix Array ( $64 × 64 × 2$ )
Layers	Convolution Kernel Size
C1+ ReLu	$128 @ (3 × 3)$ , padding, stride = 1
M1	$2 × 2$ , stride = 2
C2+ ReLu	$128 @ (3 × 3)$ , padding, stride = 1
M2	$2 × 2$ , stride = 2
C3+ ReLu	$256 @ (3 × 3)$ , padding, stride = 1
C4+ ReLu	$256 @ (3 × 3)$ , padding, stride = 1
M3	$2 × 2$ , stride = 2
F+ Sigmoid	$16 ? 384 × 64$
Output: Feature Vector (方正汇总行 $64 × 1$ )

Table 2 Hyper parameters of the proposed CNN

Input: Multicarrier Covariance Matrix Array ( $64 × 64 × 2$ )
Layers	Convolution Kernel Size
C1+ ReLu	$128 @ (3 × 3)$ , padding, stride = 1
M1	$2 × 2$ , stride = 2
C2+ ReLu	$128 @ (3 × 3)$ , padding, stride = 1
M2	$2 × 2$ , stride = 2
C3+ ReLu	$256 @ (3 × 3)$ , padding, stride = 1
C4+ ReLu	$256 @ (3 × 3)$ , padding, stride = 1
M3	$2 × 2$ , stride = 2
F+ Sigmoid	$16 ? 384 × 64$
Output: Feature Vector (方正汇总行 $64 × 1$ )

Figure 4 Receiver operating characteristic (ROC) curves of different algorithms with M = 8

Figure 5 Receiver operating characteristic (ROC) curves of different algorithms with M = 64

Figure 6 Probability of detection with different number of samples Nsymwith probability of false alarm (PFA) = 0.1

Figure 7 Probability of detection with different average SNR c under probability of false alarm (PFA) = 0.1

References 25

1	TIAN F, FENG Z, CHEN X. Spectrum occupancy measurement and analysis [J]. ZTE communications, 2009, 7(2): 16–20
2	MITOLA J, MAGUIRE G Q. Cognitive radio: making software radios more personal [J]. IEEE personal communications, 1999, 6(4): 13–18. DOI: 10.1109/98.788210 DOI
3	LIANG Y C, CHEN K C, LI G Y, et al. Cognitive radio networking and communications: an overview [J]. IEEE transactions on vehicular technology, 2011, 60(7): 3386–3407. DOI: 10.1109/TVT.2011.2158673 DOI
4	WANG H, SU X, WANG J. Cooperative spectrum sensing techniques in cognitive radio [J]. ZTE communications, 2009, 7(2): 11–15
5	DIGHAM F F, ALOUINI M S, SIMON M K. On the energy detection of unknown signals over fading channels [J]. IEEE transactions on communications, 2007, 55(1): 21–24. DOI: 10.1109/TCOMM.2006.887483 DOI
6	SONNENSCHEIN A, FISHMAN P M. Radiometric detection of spread-spectrum signals in noise of uncertain power [J]. IEEE transactions on aerospace and electronic systems, 1992, 28(3): 654–660. DOI: 10.1109/7.256287 DOI
7	TANDRA R, SAHAI A. Fundamental limits on detection in low SNR under noise uncertainty [C]//Proceedings of 2005 International Conference on Wireless Networks, Communications and Mobile Computing. IEEE, 2005: 464–469. DOI: 10.1109/WIRLES.2005.1549453 DOI
8	ZENG Y, LIANG Y C. Eigenvalue-based spectrum sensing algorithms for cognitive radio [J]. IEEE transactions on communications, 2009, 57(6): 1784–1793. DOI: 10.1109/TCOMM.2009.06.070402 DOI
9	ZHANG R, LIM T J, LIANG Y C, et al. Multi-antenna based spectrum sensing for cognitive radios: A GLRT approach [J]. IEEE transactions on communications, 2010, 58(1): 84–88. DOI: 10.1109/TCOMM.2010.01.080158 DOI
10	BOUALLEGUE K, DAYOUB I, GHARBI M, et al. Blind spectrum sensing using extreme eigenvalues for cognitive radio networks [J]. IEEE communications letters, 2018, 22(7): 1386–1389. DOI: 10.1109/LCOMM.2017.2776147 DOI
11	ZHAO W J, LI H, JIN M L, et al. Eigenvalues-based universal spectrum sensing algorithm in cognitive radio networks [J]. IEEE systems journal, 2021, 15(3): 3391–3402. DOI: 10.1109/JSYST.2020.3002941 DOI
12	LI H, ZHAO W J, JIN M L, et al. Improved spectrum sensing algorithm combining energy and eigenvalue [J]. International journal of future computer and communication, 2020: 27–32. DOI: 10.18178/ijfcc.2020.9.2.561 DOI
13	LECUN Y, BENGIO Y, HINTON G. Deep learning [J]. Nature, 2015, 521(7553): 436–444. DOI: 10.1038/nature14539 DOI
14	GUO D, ZHENG Q, PENG X, et al. Face detection, alignment, quality assessment and attribute analysis with multi-task hybrid convolutional neural networks [J]. ZTE Communications, 2019, 17(3): 15–22. DOI: 10.12142/ZTECOM.201903004 DOI
15	VYAS M R, PATEL D K, LOPEZ-BENITEZ M. Artificial neural network based hybrid spectrum sensing scheme for cognitive radio [C]//Proceedings of 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications. IEEE, 2017: 1–7. DOI: 10.1109/PIMRC.2017.8292449 DOI
16	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. DOI: 10.1109/JSAC.2019.2933892 DOI
17	XIE J D, LIU C, LIANG Y C, et al. Activity pattern aware spectrum sensing: a CNN-based deep learning approach [J]. IEEE communications letters, 2019, 23(6): 1025–1028. DOI: 10.1109/LCOMM.2019.2910176 DOI
18	XIE J D, FANG J, LIU C, et al. Deep learning-based spectrum sensing in cognitive radio: a CNN-LSTM approach [J]. IEEE communications letters, 2020, 24(10): 2196–2200. DOI: 10.1109/LCOMM.2020.3002073 DOI
19	CHEN H S, GAO W, DAUT D G. Spectrum sensing for OFDM systems employing pilot tones [J]. IEEE transactions on wireless communications, 2009, 8(12): 5862–5870. DOI: 10.1109/TWC.2009.12.080777 DOI
20	ZENG Y H, LIANG Y C, PHAM T H. Spectrum sensing for OFDM signals using pilot induced auto-correlations [J]. IEEE journal on selected areas in communications, 2013, 31(3): 353–363. DOI: 10.1109/JSAC.2013.130303 DOI
21	QUAN Z, CUI S G, SAYED A H, et al. Optimal multiband joint detection for spectrum sensing in cognitive radio networks [J]. IEEE transactions on signal processing, 2009, 57(3): 1128–1140. DOI: 10.1109/TSP.2008.2008540 DOI
22	HAMDAOUI B, KHALFI B, GUIZANI M. Compressed wideband spectrum sensing: concept, challenges, and enablers [J]. IEEE communications magazine, 2018, 56(4): 136–141. DOI: 10.1109/MCOM.2018.1700719 DOI
23	GUIMARÃES D, SILVA C DA, DE SOUZA R. Cooperative spectrum sensing using eigenvalue fusion for OFDMA and other wideband signals [J]. Journal of sensor and actuator networks, 2013, 2(1): 1–24. DOI: 10.3390/jsan2010001 DOI
24	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. DOI: 10.1109/TVT.2019.2891291 DOI
25	KINGMA D P, BA J. Adam: a method for stochastic optimization [EB/OL]. [2022-03-01].

[1]	DENG Letian, ZHAO Yanru. Deep Learning-Based Semantic Feature Extraction: A Literature Review and Future Directions [J]. ZTE Communications, 2023, 21(2): 11-17.
[2]	FAN Guotian, WANG Zhibin. Intelligent Antenna Attitude Parameters Measurement Based on Deep Learning SSD Model [J]. ZTE Communications, 2022, 20(S1): 36-43.
[3]	GAO Zhengguang, LI Lun, WU Hao, TU Xuezhen, HAN Bingtao. A Unified Deep Learning Method for CSI Feedback in Massive MIMO Systems [J]. ZTE Communications, 2022, 20(4): 110-115.
[4]	HE Hongye, YANG Zhiguo, CHEN Xiangning. Payload Encoding Representation from Transformer for Encrypted Traffic Classification [J]. ZTE Communications, 2021, 19(4): 90-97.
[5]	XUE Songyan, LI Ang, WANG Jinfei, YI Na, MA Yi, Rahim TAFAZOLLI, Terence DODGSON. To Learn or Not to Learn:Deep Learning Assisted Wireless Modem Design [J]. ZTE Communications, 2019, 17(4): 3-11.
[6]	ZHENG Xiaoqing, LU Yaping, PENG Haoyuan, FENG Jiangtao, ZHOU Yi, JIANG Min, MA Li, ZHANG Ji, JI Jie. Detecting Abnormal Start-Ups, Unusual Resource Consumptions of the Smart Phone: A Deep Learning Approach [J]. ZTE Communications, 2019, 17(2): 38-43.
[7]	ZHENG Xiaoqing, CHEN Jun, SHANG Guoqiang. Deep Neural Network-Based Chinese Semantic Role Labeling [J]. ZTE Communications, 2017, 15(S2): 58-64.
[8]	Rongzhen Yang and Hujun Yin. Uplink Power Control for MIMO-OFDMA Cellular Systems [J]. ZTE Communications, 2011, 9(4): 55-62.

Spectrum Sensing for OFDMA Using Multicarrier Covariance Matrix Aware CNN

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 25

Related Articles 8

Recommended Articles

Metrics