C-WAN for FTTR: Enabling Low-Overhead Joint Transmission with Deep Learning

doi:10.12142/ZTECOM.202504008

ZTE Communications ›› 2025, Vol. 23 ›› Issue (4): 65-76.DOI: 10.12142/ZTECOM.202504008

• Special Topic • Previous Articles Next Articles

C-WAN for FTTR: Enabling Low-Overhead Joint Transmission with Deep Learning

ZHANG Yang¹, CEN Zihan¹, ZHAN Wen²(), CHEN Xiang¹

^1.School of Electronics and Information Technology, Sun Yat?sen University, Guangzhou 510006, China
^2.School of Electronics and Communication Engineering, Sun Yat?sen University, Shenzhen 518107, China

Received:2025-09-20 Online:2025-12-25 Published:2025-12-22
About author:ZHANG Yang received his BE degree in communication engineering from Sun Yat-sen University, China in 2023. He is currently pursuing the MS degree in integrated circuit engineering at Sun Yat-sen University. His research interests include multi-AP coordination and distributed MIMO technologies.
CEN Zihan received his BE degree in electronic information engineering from Central South University, China in 2024. He is currently pursuing the MS degree in communication engineering at Sun Yat-sen University. His research interests include artificial intelligence and AI-RAN.
ZHAN Wen (zhanw6@mail.sysu.edu.cn) received his BS and MS degrees from the University of Electronic Science and Technology of China in 2012 and 2015, respectively. He obtained his PhD from the City University of Hong Kong, China in 2019, where he later worked as a research assistant and a postdoctoral fellow. Since 2020, he has been with the School of Electronics and Communication Engineering, Sun Yat-sen University, China, where he is currently an Associate Professor. His research interests include Internet of Things, modeling, and performance optimization of next-generation mobile communication systems.
CHEN Xiang received his BE and PhD degrees from the Department of Electronic Engineering, Tsinghua University, China in 2002 and 2008, respectively. From July 2008 to December 2014, he was with the Wireless and Mobile Communication Technology Research and Development Center (Wireless Center) and the Aerospace Center, Tsinghua University. In July 2005 and from September 2006 to April 2007, he visited NTT DoCoMo Research and Development (YRP), and the Wireless Communications and Signal Processing (WCSP) Laboratory, Taiwan Tsing Hua University, China. Since January 2015, he has been with the School of Electronics and Information Technology, Sun Yat-sen University, where he is currently a Full Professor. His research interests include 5G/6G wireless and mobile communication networks and the Internet of Things (IoT).

Abstract

Abstract:

Fiber-to-the-Room (FTTR) networks with multi-access point (AP) coordination face significant challenges in implementing Joint Transmission (JT), particularly the high overhead of Channel State Information (CSI) acquisition. While the centralized wireless access network (C-WAN) architecture inherently provides high-precision synchronization through fiber-based clock distribution and centralized scheduling, efficient JT still requires accurate CSI with low signaling cost. In this paper, we propose a deep learning-based hybrid model that synergistically integrates temporal prediction and spatial reconstruction to exploit spatiotemporal correlations in indoor channels. By leveraging the centralized data and computational capability of the C-WAN architecture, the model reduces sounding frequency and the number of antennas required per sounding instance. Experimental results on a real-world synchronized channel dataset show that the proposed method lowers over-the-air resource consumption while maintaining JT performance close to that achieved with ideal CSI, offering a practical low-overhead solution for high-performance FTTR systems.

Key words: Fiber-to-the-Room (FTTR), Joint Transmission (JT), centralized wireless access network (C-WAN), deep learning, Channel State Information (CSI)

ZHANG Yang, CEN Zihan, ZHAN Wen, CHEN Xiang. C-WAN for FTTR: Enabling Low-Overhead Joint Transmission with Deep Learning[J]. ZTE Communications, 2025, 23(4): 65-76.

Figures/Tables 7

Figure 1 Typical Fiber-to-the-Room (FTTR) system

Figure 2 (a) Traditional distributed Fiber-to-the-Room (FTTR) architecture; (b) FTTR/centralized wireless access network (C-WAN) architecture

Figure 3 Hybrid model architecture that fuses CNN and ResNet

Figure 4 Loss convergence curves: (a) NMSE; (b) the spectral efficiency loss function ?

Figure 5 (a) Effect of N? on the loss function; (b) Effect of N? selection strategy on the loss function

Figure 6 (a) Adaptive fusion weightα for the temporal branch and (b) performance comparison of model variants

Figure 7 Cumulative Distribution Function (CDF) of achievable spectral efficiency for different CSI acquisition methods

References 28

[1]	ZHANG D Z, ZENG T, YANG Z Y, et al. FTTR-B technology exploration and practice [C]//Proc. IEEE International Conference on Communications Workshops (ICC Workshops). IEEE, 2024: 37–41. DOI: 10.1109/ICCWorkshops59551.2024.10615937
[2]	NUNEZ D, SMITH M, BELLALTA B. Multi-AP coordinated spatial reuse for Wi-Fi 8: group creation and scheduling [C]//Proc. 21st Mediterranean Communication and Computer Networking Conference (MedComNet). IEEE, 2023: 203–208. DOI: 10.1109/MedComNet58619.2023.10168857
[3]	SHEN G X, LI J, CAI J H, et al. Enhancing fiber-to-the-room (FTTR) technologies: addressing key challenges and solutions (invited tutorial) [C]//Proc. Conference on Lasers and Electro-Optics Pacific Rim (CLEO-PR). IEEE, 2024: 1–2. DOI: 10.1109/CLEO-PR60912.2024.10676562
[4]	SUNDARAVARADHAN S P, PORAT R, TOUSSI K N. Increasing spatial multiplexing gain in future multi-AP WiFi systems via joint transmission [J]. IEEE communications standards magazine, 2022, 6(2): 20–26. DOI: 10.1109/MCOMSTD.0001.2100085
[5]	CHEN B H, JIAO X J, LIU W, et al. An experimental study of Wi-Fi joint transmission with multiple openwifi access points [C]//IEEE Wireless Communications Networking Conference (WCNC). IEEE, 2025: 1–67. DOI: 10.1109/WCNC61545.2025.10978612
[6]	HAMED E, RAHUL H, ABDELGHANY M A, et al. Real-time distributed MIMO systems [C]//Proc. 2016 ACM SIGCOMM Conference (SIGCOMM ' 16. Association for Computing Machinery, 2016: 412–425. DOI: 10.1145/2934872.2934905
[7]	TITUS A, BANSAL R, SREEJITH T V, et al. Decision problems for joint transmission in multi-AP coordination framework of IEEE 802.11be [C]//Proc. International Conference on COMmunication Systems & NETworkS (COMSNETS). IEEE, 2021: 326–333. DOI: 10.1109/COMSNETS51098.2021.9352818
[8]	LEVINBOOK Y, EZRI D, MELZER E. AP cooperation in Wi-Fi: joint transmission with a novel precoding scheme, resilient to phase offsets between transmitters [J]. Signal processing, 2024, 220: 109432. DOI: 10.1016/j.sigpro.2024.109432
[9]	KUNNATH GANESAN U, SARVENDRANATH R, LARSSON E G. BeamSync: over-the-air synchronization for distributed massive MIMO systems [J]. IEEE transactions on wireless communications, 2024, 23(7): 6824–6837. DOI: 10.1109/TWC.2023.3335089
[10]	HE J L, YAO H, ZHAO D S, et al. Multi-channel phase synchronization method for independent asynchronous local oscillators based on pre-calibration matrix [C]//Proc. IEEE International Symposium on Antennas and Propagation and INC/USNC‐URSI Radio Science Meeting (AP-S/INC-USNC-URSI). IEEE, 2024: 449–450. DOI: 10.1109/AP-S/INC-USNC-URSI52054.2024.10687303
[11]	VERMA S, RODRIGUES T K, KAWAMOTO Y, et al. A survey on multi-AP coordination approaches over emerging WLANs: future directions and open challenges [J]. IEEE communications surveys & tutorials, 2024, 26(2): 858–889. DOI: 10.1109/COMST.2023.3344167
[12]	LIU Z Y, ZHANG L, DING Z. Overcoming the channel estimation barrier in massive MIMO communication via deep learning [J]. IEEE wireless communications, 2020, 27(5): 104–111. DOI: 10.1109/MWC.001.1900413
[13]	JIANG W, SCHOTTEN H D. Deep learning for fading channel prediction [J]. IEEE open journal of the communications society, 2020, 1: 320–332. DOI: 10.1109/OJCOMS.2020.2982513
[14]	CHEN W, WAN W X, WANG S Y, et al. CSI-PPPNet: a one-sided one-for-all deep learning framework for massive MIMO CSI feedback [J]. IEEE transactions on wireless communications, 2024, 23(7): 7599–7611. DOI: 10.1109/TWC.2023.3342735
[15]	BANERJEE B, ELLIOTT R C, KRZYMIEŃ W A, et al. Machine learning assisted DL CSI estimation for high-mobility multi-antenna users with partial UL CSI availability in TDD massive MIMO systems [C]//Proc. IEEE Globecom Workshops (GC Wkshps). IEEE, 2022: 1579–1585. DOI: 10.1109/GCWkshps56602.2022.10008644
[16]	WANG J Z, LIU W C, MENG J, et al. Fiber to the radio/C-WAN architecture and its performance analysis [C]//Proc. IEEE International Conference on Communications Workshops (ICC Workshops). IEEE, 2024: 709–713. DOI: 10.1109/ICCWorkshops59551.2024.10615771
[17]	ZHENG J K, ZHANG J Y, BJÖRNSON E, et al. Impact of channel aging on cell-free massive MIMO over spatially correlated channels [J]. IEEE transactions on wireless communications, 2021, 20(10): 6451–6466. DOI: 10.1109/TWC.2021.3074421
[18]	EUCHNER F, KELLNER D, STEPHAN P, et al. CSI dataset espargos-0005: four phase- and time-synchronous ESPARGOS antenna arrays in a lab room [EB/OL]. [2020-05-01].
[19]	VIEIRA J, RUSEK F, TUFVESSON F. Reciprocity calibration methods for massive MIMO based on antenna coupling [C]//2014 IEEE Global Communications Conference. IEEE, 2014: 3708–3712. DOI: 10.1109/GLOCOM.2014.7037384 .
[20]	WU X M, ZENG Y, SI X S, et al. Fiber-to-the-room (FTTR): standards and deployments [C]//Proc. Optical Fiber Communication Conference (OFC) 2023. Optica Publishing Group, 2023: 1–3. DOI: 10.1364/ofc.2023.tu3f.6
[21]	JIMÉNEZ LÓPEZ M, GUTIÉRREZ RIVAS J L, DÍAZ ALONSO J. A white-rabbit network interface card for synchronized sensor networks [C]//Proc. SENSORS, 2014 IEEE. IEEE, 2014: 2000–2003. DOI: 10.1109/ICSENS.2014.6985426
[22]	XU Y L, RAJAGOPALA A D, FRUITWALA N, et al. Multi-FPGA synchronization and data communication for quantum control and measurement [EB/OL]. [2025-06-11].
[23]	BALAN H V, ROGALIN R, MICHALOLIAKOS A, et al. AirSync: enabling distributed multiuser MIMO with full spatial multiplexing [J]. IEEE/ACM transactions on networking, 2013, 21(6): 1681–1695. DOI: 10.1109/TNET.2012.2230449
[24]	LIU X, LI J W, WU X M, et al. Fiber-to-the-room (FTTR) technologies for the 5th generation fixed network (F5G) and beyond [C]//Proc. IEEE Future Networks World Forum (FNWF). IEEE, 2022: 351–354. DOI: 10.1109/FNWF55208.2022.00068
[25]	LI J L, ZHANG Q, XIN X J, et al. Deep learning-based massive MIMO CSI feedback [C]//18th International Conference on Optical Communications and Networks (ICOCN). IEEE, 2019: 1–3. DOI: 10.1109/ICOCN.2019.8934725
[26]	NAKAMURA T, BOUAZIZI M, YAMAMOTO K, et al. Wi-Fi-based fall detection using spectrogram image of channel state information [J]. IEEE Internet of Things journal, 2022, 9(18): 17220–17234. DOI: 10.1109/JIOT.2022.3152315
[27]	SEGUEL F, SALIHU D, HAEGELE S, et al. Complex-valued deep learning for WiFi-based indoor positioning: method and performance [C]//European Wireless 2024; 29th European Wireless Conference. VDE, 2024: 59–65
[28]	BAI S J, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling [EB/OL]. [2018-04-19].

C-WAN for FTTR: Enabling Low-Overhead Joint Transmission with Deep Learning

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 28

Related Articles 15

Recommended Articles

Metrics

[1]	LIU Yichen, GAO Ruixin, ZENG Chen, LIU Yingzhuang. A Transformer-Based End-to-End Receiver Design for Wi-Fi 7 Physical Layer [J]. ZTE Communications, 2025, 23(4): 27-36.
[2]	HE Shuai, LIU Limin, WANG Zhanli, LI Jinliang, MAO Xiaojun, MING Anlong. M+MNet: A Mixed-Precision Multibranch Network for Image Aesthetics Assessment [J]. ZTE Communications, 2025, 23(3): 96-110.
[3]	AI Bo, ZHANG Yuxin, YANG Mi, HE Ruisi, GUO Rongge. A Machine Learning-Based Channel Data Enhancement Platform for Digital Twin Channels [J]. ZTE Communications, 2025, 23(2): 20-30.
[4]	CHENG Jiaming, CHEN Wei, LI Lun, AI Bo. Efficient Spatio-Temporal Predictive Learning for Massive MIMO CSI Prediction [J]. ZTE Communications, 2025, 23(1): 3-10.
[5]	WANG Chongchong, LI Yao, WANG Beibei, CAO Hong, ZHANG Yanyong. Point Cloud Processing Methods for 3D Point Cloud Detection Tasks [J]. ZTE Communications, 2023, 21(4): 38-46.
[6]	GONG Panyin, ZHANG Guidong, ZHANG Zhigang, CHEN Xiao, DING Xuan. Research on Fall Detection System Based on Commercial Wi-Fi Devices [J]. ZTE Communications, 2023, 21(4): 60-68.
[7]	DENG Letian, ZHAO Yanru. Deep Learning-Based Semantic Feature Extraction: A Literature Review and Future Directions [J]. ZTE Communications, 2023, 21(2): 11-17.
[8]	LU Ping, SHENG Bin, SHI Wenzhe. Scene Visual Perception and AR Navigation Applications [J]. ZTE Communications, 2023, 21(1): 81-88.
[9]	FAN Guotian, WANG Zhibin. Intelligent Antenna Attitude Parameters Measurement Based on Deep Learning SSD Model [J]. ZTE Communications, 2022, 20(S1): 36-43.
[10]	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.
[11]	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.
[12]	HE Hongye, YANG Zhiguo, CHEN Xiangning. Payload Encoding Representation from Transformer for Encrypted Traffic Classification [J]. ZTE Communications, 2021, 19(4): 90-97.
[13]	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.
[14]	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.
[15]	ZHENG Xiaoqing, CHEN Jun, SHANG Guoqiang. Deep Neural Network-Based Chinese Semantic Role Labeling [J]. ZTE Communications, 2017, 15(S2): 58-64.