Prediction-Window Aided Fluid Antenna Systems for High-Mobility Communications

doi:10.12142/ZTECOM.202603004

ZTE Communications ›› 2026, Vol. 24 ›› Issue (3): 18-30.DOI: 10.12142/ZTECOM.202603004

• Special Topic • Previous Articles Next Articles

Prediction-Window Aided Fluid Antenna Systems for High-Mobility Communications

Huang Yinning¹(), Zeng Cheng¹, Yang Zhaohui²

^1.Nanjing University of Science and Technology, Nanjing 210094, China
^2.Zhejiang University, Hangzhou 310058, China

Received:2026-06-17 Online:2026-09-20 Published:2026-09-20
About author:Huang Yinning (922104780107@njust.edu.cn) received her BEng degree from Nanjing University of Science and Technology, China in 2026. She was admitted directly to the MS program at the same university without the entrance examination in the same year. Her current research interests include fluid antenna systems, embodied intelligence, and wireless transmission optimization for mobile scenarios.
Zeng Cheng is an Associate Professor with the School of Electronic and Optical Engineering, Nanjing University of Science and Technology, China and the QianTang Advanced Research Institute on Information, Zhejiang Key Laboratory of Intelligent Metasurface and System, China. He was a Visiting PhD Student at KTH Royal Institute of Technology, Sweden (2022–2023) and a Research Assistant at Chinese University of Hong Kong, Shenzhen (2024–2025). His current research interests include image processing and pattern recognition.
Yang Zhaohui received his bachelor's and PhD degrees from Southeast University, China in 2014 and 2018, respectively. From 2018 to 2020, he was a Postdoctoral Research Associate with the Center for Telecommunications Research, Department of Informatics, King's College London, UK. From 2020 to 2022, he was a research fellow with the Department of Electronic and Electrical Engineering, University College London, UK. He is currently a ZJU Hundred-Talent Program Research Fellow and doctoral supervisor with the Zhejiang Key Laboratory of Information Processing Communication and Networking, College of Information Science and Electronic Engineering, Zhejiang University, China. He is a recipient of the National Young Talent Program and the Young Talent Support Project of the China Association for Science and Technology. His research interests include integrated intelligent communication, sensing and computing, federated learning, fluid antenna networks, and joint resource optimization. He serves as an Associate Editor for multiple IEEE flagship journals and Guest Editor for IEEE JSAC and other transactions. He has received several IEEE international paper awards including the IEEE Communications Society Asia-Pacific Outstanding Young Researcher Award.
Supported by:
the National Natural Science Foundation of China(62601386);the Basic Research Program of Jiangsu Province(BK20251413);the State Key Laboratory of Millimeter Waves(K202602?01);the Fundamental Research Funds for the Central Universities(30925010508)

Abstract

Abstract:

Fluid antenna systems (FAS) provide continuous spatial degrees of freedom for next-generation wireless networks. However, deploying FAS on high-speed mobile embodied intelligent agents introduces Doppler shifts that shorten the channel coherence time, causing conventional full-port scanning to incur excessive pilot overhead. To address this issue, this paper proposes a prediction-aided adaptive communication architecture that constructs a dynamic local sounding window centered on upper-layer prediction results. By exploiting the spatial channel correlation among FAS ports, the proposed approach balances pilot overhead and spatial diversity gain under prediction deviations. We establish a quantitative model for the long-term expected throughput by integrating a nonlinear bounded hit probability function and a gain bridging model based on the zeroth-order Bessel function of the first kind. We then formulate a discrete optimization problem under practical constraints to maximize the expected transmission capacity, and develop a two-stage low-complexity algorithm that decouples the online computational complexity from the number of antenna ports. Simulation results show that the proposed mechanism adaptively adjusts the sounding window size according to moving velocity and prediction accuracy, reducing pilot overhead in high-mobility scenarios and achieving higher throughput than fixed-window and global scanning schemes.

Key words: fluid antenna system, embodied intelligent agent, overhead catastrophe, prediction window, discrete zeroth-order gradient optimization

Huang Yinning, Zeng Cheng, Yang Zhaohui. Prediction-Window Aided Fluid Antenna Systems for High-Mobility Communications[J]. ZTE Communications, 2026, 24(3): 18-30.

Figures/Tables 8

Figure 1 System Diagram of an FAS-enabled agent served by a base station in a multipath environment

Figure 2 Timing diagram of pilot overhead and effective data transmission within one channel coherence time Tc?, comparing the proposed prediction-aided local sounding (FAS+AI) with conventional full-port scanning (FAS)

Figure 3 Schematic diagram of spatial relationship for 2D FAS

Figure 4 Simulation results of R versus K: (a) τ0=0.01?ms,??p0=0.2; (b) τ0=0.01?ms,??p0=0.5; (c) τ0=0.01?ms,??p0=0.9; (d) τ0=0.05?ms,??p0=0.2; (e) τ0=0.05?ms,??p0=0.5; (f) τ0=0.05?ms,??p0=0.9

Figure 5 Simulation results of R versus v: (a) τ0=0.01?ms,??p0=0.2; (b) τ0=0.01?ms,??p0=0.5; (c) τ0=0.01?ms,??p0=0.9; (d) τ0=0.05?ms,??p0=0.2; (e) τ0=0.05?ms,??p0=0.5; (f) τ0=0.05?ms,??p0=0.9

Figure 6 Adaptive adjustment of optimal window size with prediction accuracy and moving velocity: (a) τ0=0.01?ms; (b) τ0=0.05?ms

Figure 7 Effective throughput R versus prediction accuracy p0 under different moving velocities: (a) τ0=0.01?ms; (b) τ0=0.05?ms

Figure 8 Monte Carlo validation of the spatial bridging model

References 25

[1]	Liu H P, Guo D, Cangelosi A. Embodied intelligence: a synergy of morphology, action, perception and learning [J]. ACM computing surveys, 2025, 57(7): 1–36. DOI: 10.1145/3717059
[2]	Gao Y, Chen J J, Li D P. Intelligence driven wireless networks in B5G and 6G era: a survey [J]. ZTE communications, 2024, 22(3): 99–105. DOI: 10.12142/ZTECOM.202403012
[3]	Wong K K, Shojaeifard A, Tong K F, et al. Fluid antenna systems [J]. IEEE transactions on wireless communications, 2021, 20(3): 1950–1962. DOI: 10.1109/TWC.2020.3037595
[4]	Wong K K, Tong K F. Fluid antenna multiple access [J]. IEEE transactions on wireless communications, 2022, 21(7): 4801–4815. DOI: 10.1109/TWC.2021.3133410
[5]	Wong K K, Shojaeifard A, Tong K F, et al. Performance limits of fluid antenna systems [J]. IEEE communications letters, 2020, 24(11): 2469–2472. DOI: 10.1109/LCOMM.2020.3006554
[6]	Wong K K, Chae C B, Tong K F. Compact ultra massive antenna array: a simple open-loop massive connectivity scheme [J]. IEEE transactions on wireless communications, 2024, 23(6): 6279–6294. DOI: 10.1109/TWC.2023.3330932
[7]	Xu H, Wong K K, New W K, et al. Capacity maximization for FAS-assisted multiple access channels [J]. IEEE transactions on communications, 2025, 73(7): 4713–4731. DOI: 10.1109/TCOMM.2024.3516499
[8]	Zhang Q, Shao M J, Zhang T, et al. An efficient sum-rate maximization algorithm for fluid antenna-assisted ISAC system [J]. IEEE communications letters, 2025, 29(1): 200–204. DOI: 10.1109/LCOMM.2024.3510334
[9]	Zhang Z J, Zhu J A, Dai L L, et al. Successive Bayesian reconstructor for channel estimation in fluid antenna systems [J]. IEEE transactions on wireless communications, 2025, 24(3): 1992–2006. DOI: 10.1109/TWC.2024.3515135
[10]	Xu B W, Chen Y, Cui Q M, et al. Sparse Bayesian learning-based channel estimation for fluid antenna systems [J]. IEEE wireless communications letters, 2025, 14(2): 325–329. DOI: 10.1109/LWC.2024.3500218
[11]	Xiao Z Y, Cao S Q, Zhu L P, et al. Channel estimation for movable antenna communication systems: a framework based on compressed sensing [J]. IEEE transactions on wireless communications, 2024, 23(9): 11814–11830. DOI: 10.1109/TWC.2024.3385110
[12]	Tang E Q, Guo W, He H T, et al. Accurate and fast channel estimation for fluid antenna systems with diffusion models [PP/OL]. V1. arXiv (2025-05-08)[2025-08-19].
[13]	Zhang H B, Wang J L, Wang C, et al. Learning-induced channel extrapolation for fluid antenna systems using asymmetric graph masked autoencoder [J]. IEEE wireless communications letters, 2024, 13(6): 1665–1669. DOI: 10.1109/LWC.2024.3386153
[14]	Ji S Y, Psomas C, Thompson J. Correlation-based machine learning techniques for channel estimation with fluid antennas [C]//Proceedings of ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2024: 8891–8895. DOI: 10.1109/ICASSP48485.2024.10447499
[15]	Pakravan S, Ahmadzadeh M, Zeng M, et al. Fluid antenna systems under channel uncertainty and hardware impairments: trends, challenges, and future research directions [PP/OL]. V1. arXiv (2026-01-30)[2026-04-01].
[16]	Deng T S, Gao Y, Zhang T, et al. Integrating large language models into fluid antenna systems: a survey [J]. Sensors, 2025, 25(16): 5177. DOI: 10.3390/s25165177
[17]	Zhang Y L, Yin H F, Li W D, et al. Fluid antenna port prediction based on large language models [C]//Proceedings of 2025 IEEE Global Communications Conference. IEEE, 2025: 4934–4939. DOI: 10.1109/GLOBECOM59602.2025.11432485
[18]	Chai Z, Wong K K, Tong K F, et al. Port selection for fluid antenna systems [J]. IEEE communications letters, 2022, 26(5): 1180–1184. DOI: 10.1109/LCOMM.2022.3152451
[19]	Wong K K, Tong K F, Chen Y, et al. Closed-form expressions for spatial correlation parameters for performance analysis of fluid antenna systems [J]. Electronics letters, 2022, 58(11): 454–457. DOI: 10.1049/ell2.12487
[20]	Shan Y R, Wang F G, Hao Y X, et al. Doppler rate estimation for OTFS via large-scale antenna array [J]. ZTE Communications, 2025, 23(1): 115–122. DOI: 10.12142/ZTECOM.202501015
[21]	Liu Zhipeng L K. Dual-polarized 2D beam-scanning antenna based on reconfigurable reflective elements [J]. ZTE communications, 2025, 23(1): 85–89. DOI: 10.12142/ZTECOM.202501011
[22]	Lu M Y, Bai L, Han Z R, et al. 6G digital twin enabled channel modeling for Beijing central business district [J]. ZTE Communications, 2025, 23(2): 31–45. DOI: 10.12142/ZTECOM.202502005
[23]	Zhang Z T, Xu J Y, Wong K K, et al. Finite-aperture planar fluid antenna array [PP/OL]. V1. arXiv (2026-05-21) [2026-05-25].
[24]	Zhang L, Zhao Y Z, Yang H, et al. Enhanced fluid index modulation for integrated data and energy transfer [PP/OL]. V1. arXiv (2026-06-03) [2026-06-05].
[25]	Ahmadzadeh M, Pakravan S, Ajib W, et al. Performance analysis of fluid antenna-assisted over-the-air federated learning under spatially correlated fading [J]. IEEE Internet of Things journal, 2026, 13(16): 37462–37472. DOI: 10.1109/JIOT.2026.3701371

Prediction-Window Aided Fluid Antenna Systems for High-Mobility Communications

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 25

Related Articles 2

Recommended Articles

Metrics

[1]	Wu Ruojia, Xu Rui, Ye Yinghui, Song Xi, Lu Guangyue. Closed-Form Outage Expression of Fluid Antenna Systems for Ultra-Reliable Communications [J]. ZTE Communications, 2026, 24(3): 3-11.
[2]	Wu Tuo, Wu Zhenguan, Zhi Kangda, Liu Baiyang, Tong Kin‑Fai. Equivalent Degrees of Freedom Based Secrecy Outage Analysis for Fluid Antenna Wiretap Channels [J]. ZTE Communications, 2026, 24(3): 12-17.