Efficient PSS Detection Algorithm Aided by CNN

doi:10.12142/ZTECOM.202501008

ZTE Communications ›› 2025, Vol. 23 ›› Issue (1): 63-70.DOI: 10.12142/ZTECOM.202501008

收稿日期:2025-01-10 出版日期:2025-03-25 发布日期:2025-03-25

Efficient PSS Detection Algorithm Aided by CNN

LI Lanlan()

Shanghai Technical Institute of Electronics & Information, Shanghai 201141, China

Received:2025-01-10 Online:2025-03-25 Published:2025-03-25
About author:LI Lanlan (403197915@qq.com) received her MS degree in applied mathematics from Xinjiang University, China in 2001, and PhD degree in electrical engineering from Southeast University, China in 2005. She is currently engaged in teaching and research at the Shanghai Technical Institute of Electronics & Information, China. From 2019 to 2022, she worked as a researcher in intelligent communication at the Purple Mountain Laboratories, China. Her research interests include radio resource management, signal processing for digital communications, 6G communication technology, and AI-related applications in communication.

摘要/Abstract

Abstract:

In a 5G mobile communication system, cell search is the initial step in establishing downlink synchronization between user equipment (UE) and base stations (BS). Primary synchronization signal (PSS) detection is a crucial part of this process, and enhancing PSS detection speed can reduce communication latency and improve overall quality. This paper proposes a fast PSS detection algorithm based on the correlation characteristics of PSS time-domain superposition signals. Conducting PSS signal correlation within a smaller range can reduce computational complexity and accelerates communication speed. Additionally, frequency offset can impact the accuracy of calculations during the PSS detection process. To address this issue, we propose applying convolutional neural networks (CNN) for frequency offset estimation of synchronization signals. By compensating for the frequency of related signals, the accuracy of PSS detection is improved. Finally, the analysis and simulation results demonstrate the effectiveness of the proposed approach.

Key words: 5G, CNN, cell search, PSS detection

. [J]. ZTE Communications, 2025, 23(1): 63-70.

LI Lanlan. Efficient PSS Detection Algorithm Aided by CNN[J]. ZTE Communications, 2025, 23(1): 63-70.

图/表 10

Figure 1 Traditional PSS detection algorithm

Table 1 Global synchronization grid

N*1 200 kHz+M*50 kHz,

N=1:2 499, M $∈$ (1,3,5)

3N+(M-3)/2

2–7 498

3 000–24 250

3 000 MHz+N*1.44 MHz,

N=0:14 756

7 499+N

7 498–22 255

Table 1 Global synchronization grid

Frequency Range/MHz

SSB

GSCN

GSCN Range

0–3 000

N*1 200 kHz+M*50 kHz,

N=1:2 499, M $∈$ (1,3,5)

3N+(M-3)/2

2–7 498

3 000–24 250

3 000 MHz+N*1.44 MHz,

N=0:14 756

7 499+N

7 498–22 255

Figure 2 Structure of synchronization signal block

Figure 3 Correlation peaks of superimposed signals

Table 2 Simulation parameters for cell search

Simulation Parameter Types	Configuration Parameters
Channel bandwidth/MHz	100
Subcarrier spacing/kHz	15, 30
The number of FFT points	1 024, 4 096
Channel mode	TDL-A,CDL-A
Sampling frequency/MHz	122.88
Frequency offset/kHz	0.2, 0.8, 2.8
SSBblock type	Case C
CPtype	Standard

Figure 4 Correlation peak plot calculated by proposed algorithm

Figure 5 Probability of primary synchronization signal search algorithm

Figure 6 Time consumption difference between proposed algorithm and existing algorithm

Figure 7 Accuracy of synchronization under different frequency offsets

Figure 8 Basic structure of convolutional neural networks

参考文献 21

1	JEON Y, PARK H, CHOI E. Synchronization and cell search procedure in 3GPP 5G NR systems [C]//The 21st International Conference on Advanced Communication Technology (ICACT). IEEE, 2019: 475–478
2	CHAKRAPANI A. On the design details of SS/PBCH, signal generation and PRACH in 5G-NR [J]. IEEE access, 2020, 8: 136617–136637. DOI: 10.1109/ACCESS.2020.3010500
3	BALASUBRAMANYA N M, LAMPE L, VOS G, et al. On timing reacquisition and enhanced primary synchronization signal (ePSS) design for energy efficient 3GPP LTE MTC [J]. IEEE transactions on mobile computing, 2016, 16(8): 2292–2305. DOI: 10.1109/TMC.2016.2618865
4	VANKAYALA S K, AKHTAR J, ASHOK KRISHNAN K S, et al. Accelerated detection schemes for PSS in 5G-NR [C]//Proceedings of IEEE 3rd 5G World Forum (5GWF). IEEE, 2020. DOI: 10.1109/5gwf49715.2020.9221156
5	YOU Y H. Reduced complexity frequency ambiguity resolution and synchronization signal detection for 5G NR-V2X communication systems [J]. IEEE systems journal, 2022, 16(1): 1325–1333. DOI: 10.1109/JSYST.2021.3058673
6	LI G Q, XU Y H, LIN J Z, et al. Res-DNN based signal detection algorithm for end-to-end MIMO systems [J]. Chinese journal on Internet of Things, 2022, 6(1): 65–72. DOI: 10.11959/j.issn.2096-3750.2022.00256
7	OMRI A, SHAQFEH M, ALI A, et al. Synchronization procedure in 5G NR systems [J]. IEEE access, 2019, 7: 41286–41295. DOI: 10.1109/ACCESS.2019.2907970
8	VAN DE BEEK J J, SANDELL M, BORJESSON P O. ML estimation of time and frequency offset in OFDM systems [J]. IEEE transactions on signal processing, 1997, 45(7): 1800–1805. DOI: 10.1109/78.599949
9	CHIU K L, SHEN P H, LIN B R, et al. Design of downlink synchronization for millimeter wave cellular system based on multipath division multiple access [J]. IEEE transactions on circuits and systems I: regular papers, 2020, 67(9): 3211–3223. DOI: 10.1109/TCSI.2020.2989467
10	YIN J L, LEE M C, HSIAO W H, et al. A novel network resolved and mobile assisted cell search method for 5G cellular communication systems [J]. IEEE access, 2022, 10: 75331–75342. DOI: 10.1109/ACCESS.2022.3191357
11	RICCARDO TUNINATO. Algorithms for New Radio synchronization layer functions [D]. Turin: Politecnico di Torino, 2020.
12	ASSAF M, PONOMAREV O G. Efficient and low complexity frequency synchronization in NR-5G downlink [C]//The 25th International Conference on Digital Signal Processing and its Applications (DSPA). IEEE, 2023: 1–6. DOI: 10.1109/DSPA57594.2023.10113363
13	KWAK B J, KIM J K, MYUNG J H, et al. A novel approach for enhancing 5G NR PSS detection with non-matched filter [C]//The 15th International Conference on Information and Communication Technology Convergence (ICTC). IEEE, 2024: 1642–1643. DOI: 10.1109/ICTC62082.2024.10827761
14	ZHANG C L, WU Q, ZHAO X W, et al. A scheme for improving 5G cell search performance [C]//The 5th International Conference on Communications, Information System and Computer Engineering (CISCE). IEEE, 2023: 141–145. DOI: 10.1109/CISCE58541.2023.10142271
15	COUTINHO F D L, SILVA H S, GEORGIEVA P, et al. A novel CNN-based channel estimation algorithm in the presence of phase noise and CFO [J]. IEEE wireless communications letters, 2024, 13(1): 193–197. DOI: 10.1109/LWC.2023.3325129
16	ZHENG H, ZHOU C, VOROBOYV S A, et al. Decomposed CNN for sub-nyquist tensor-based 2-D DOA estimation [J]. IEEE signal processing letters, 2023, 30: 1708–1712
17	ASSAF M, PONOMAREV O G. On DMRS tracking mode synchronization in fifth generation new radio [C]//Proceedings of 24th International Conference on Digital Signal Processing and its Applications (DSPA). IEEE, 2022: 1–6. DOI: 10.1109/DSPA53304.2022.9790773
18	3GPP. 3GPP technical specification group radio access network; physical channels and modulation: TS38.211 [S]. 2022
19	WANG D, MEI Z Q, ZHANG H Q, et al. A novel PSS timing synchronization algorithm for cell search in 5G NR system [J]. IEEE access, 2021, 9: 5870-5880
20	HE Y X, GU Y, BU S Q, et al. Primary synchronization signal design for New Radio technique in 5G communication system [EB/OL]. (2017-12-08)[2024-10-06].
21	LI L L, YI Y S, ZHANG C, et al. Interactive methods, devices, equipment, and storage media for wireless networks (in Chinese) [R]. Nanjing, China: Purple Mountain Laboratories, 2020

Efficient PSS Detection Algorithm Aided by CNN

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 21

相关文章 0

编辑推荐

Metrics