1.
Linfu, Zou; Zhiwen, Pan; El-Hajjar, Mohammed
Graph Neural Network Aided Beamforming for Holographic Millimeter Wave MIMO Systems Journal Article
In: IEEE Transactions on Vehicular Technology, vol. 74, no. 7, pp. 10582–10595, 2025, ISSN: 1939-9359.
Abstract | Links | BibTeX | Tags: Accuracy, Array signal processing, Beamforming, Channel estimation, Downlink, Estimation, graph neural network, Graph neural networks, holographic MIMO, millimeter wave, Millimeter wave communication, OFDM, Optimization, Training
@article{linfu_graph_2025,
title = {Graph Neural Network Aided Beamforming for Holographic Millimeter Wave MIMO Systems},
author = {Zou Linfu and Pan Zhiwen and Mohammed El-Hajjar},
url = {https://ieeexplore.ieee.org/document/10896848},
doi = {10.1109/TVT.2025.3544063},
issn = {1939-9359},
year = {2025},
date = {2025-07-01},
urldate = {2025-10-08},
journal = {IEEE Transactions on Vehicular Technology},
volume = {74},
number = {7},
pages = {10582–10595},
abstract = {Holographic multiple-input multiple-output (HMIMO) systems are considered as one of the potential techniques to meet the demands of next-generation communications by replacing costly and power-hungry devices with sub-half-wavelength antenna elements. However, optimizing the beamforming matrix in the base station (BS) for HMIMO systems is challenging, given the prohibitive overhead of directly estimating the channels between the BS and the user equipment. Instead of following the traditional method of channel estimation and beamforming optimization, in this paper we employ a deep-learning technique to optimize the beamformers at the BS based on a loss function. Specifically, in this paper we introduce a graph neural network (GNN) designed to map the received pilot signals to optimized beamforming matrices and to model interactions among user equipment within the network. The simulation results show that our deep-learning method effectively maximizes the sum-rate objective while using reduced number of pilots than traditional channel estimation and beamforming optimization techniques.},
keywords = {Accuracy, Array signal processing, Beamforming, Channel estimation, Downlink, Estimation, graph neural network, Graph neural networks, holographic MIMO, millimeter wave, Millimeter wave communication, OFDM, Optimization, Training},
pubstate = {published},
tppubtype = {article}
}
Holographic multiple-input multiple-output (HMIMO) systems are considered as one of the potential techniques to meet the demands of next-generation communications by replacing costly and power-hungry devices with sub-half-wavelength antenna elements. However, optimizing the beamforming matrix in the base station (BS) for HMIMO systems is challenging, given the prohibitive overhead of directly estimating the channels between the BS and the user equipment. Instead of following the traditional method of channel estimation and beamforming optimization, in this paper we employ a deep-learning technique to optimize the beamformers at the BS based on a loss function. Specifically, in this paper we introduce a graph neural network (GNN) designed to map the received pilot signals to optimized beamforming matrices and to model interactions among user equipment within the network. The simulation results show that our deep-learning method effectively maximizes the sum-rate objective while using reduced number of pilots than traditional channel estimation and beamforming optimization techniques.
2.
Gadamsetty, Pavan Kumar; Hari, K. V. S.; Hanzo, Lajos
Sum-Rate Maximization of RIS-Aided Digital and Holographic Beamformers in MU-MISO Systems Journal Article
In: IEEE Transactions on Communications, vol. 73, no. 5, pp. 3106–3118, 2025, ISSN: 1558-0857.
Abstract | Links | BibTeX | Tags: alternating maximization (AM), Array signal processing, Arrays, Beamforming, Millimeter wave communication, MISO communication, Programming, Radio frequency, Reconfigurable holographic surfaces (RHS), reconfigurable intelligent surfaces (RIS), Signal to noise ratio, sum-rate, Transceivers, Vectors, Wireless communication
@article{kumar_gadamsetty_sum-rate_2025,
title = {Sum-Rate Maximization of RIS-Aided Digital and Holographic Beamformers in MU-MISO Systems},
author = {Pavan Kumar Gadamsetty and K. V. S. Hari and Lajos Hanzo},
url = {https://ieeexplore.ieee.org/document/10737121},
doi = {10.1109/TCOMM.2024.3487305},
issn = {1558-0857},
year = {2025},
date = {2025-05-01},
urldate = {2025-10-08},
journal = {IEEE Transactions on Communications},
volume = {73},
number = {5},
pages = {3106–3118},
abstract = {Reconfigurable holographic surfaces (RHS) are intrinsically amalgamated with reconfigurable intelligent surfaces (RIS), for beneficially ameliorating the signal propagation environment. This potent architecture significantly improves the system performance in non-line-of-sight scenarios at a low power consumption. Briefly, the RHS technology integrates ultra-thin, lightweight antennas onto the transceiver, for creating sharp, high-gain directional beams. We formulate a user sum-rate maximization problem for our RHS-RIS-based hybrid beamformer. Explicitly, we jointly design the digital, holographic, and passive beamformers for maximizing the sum-rate of all user equipment (UE). To tackle the resultant nonconvex optimization problem, we propose an alternating maximization (AM) framework for decoupling and iteratively solving the subproblems involved. Specifically, we employ the zero-forcing criterion for the digital beamformer, leverage fractional programming to determine the radiation amplitudes of the RHS and utilize the Riemannian conjugate gradient algorithm for optimizing the RIS phase shift matrix of the passive beamformer. Our simulation results demonstrate that the proposed RHS-RIS-based hybrid beamformer outperforms its conventional counterpart operating without an RIS in multi-UE scenarios. The sum-rate improvement attained ranges from 8 bps/Hz to 13 bps/Hz for various transmit powers at the base station (BS) and at the UEs, which is significant.},
keywords = {alternating maximization (AM), Array signal processing, Arrays, Beamforming, Millimeter wave communication, MISO communication, Programming, Radio frequency, Reconfigurable holographic surfaces (RHS), reconfigurable intelligent surfaces (RIS), Signal to noise ratio, sum-rate, Transceivers, Vectors, Wireless communication},
pubstate = {published},
tppubtype = {article}
}
Reconfigurable holographic surfaces (RHS) are intrinsically amalgamated with reconfigurable intelligent surfaces (RIS), for beneficially ameliorating the signal propagation environment. This potent architecture significantly improves the system performance in non-line-of-sight scenarios at a low power consumption. Briefly, the RHS technology integrates ultra-thin, lightweight antennas onto the transceiver, for creating sharp, high-gain directional beams. We formulate a user sum-rate maximization problem for our RHS-RIS-based hybrid beamformer. Explicitly, we jointly design the digital, holographic, and passive beamformers for maximizing the sum-rate of all user equipment (UE). To tackle the resultant nonconvex optimization problem, we propose an alternating maximization (AM) framework for decoupling and iteratively solving the subproblems involved. Specifically, we employ the zero-forcing criterion for the digital beamformer, leverage fractional programming to determine the radiation amplitudes of the RHS and utilize the Riemannian conjugate gradient algorithm for optimizing the RIS phase shift matrix of the passive beamformer. Our simulation results demonstrate that the proposed RHS-RIS-based hybrid beamformer outperforms its conventional counterpart operating without an RIS in multi-UE scenarios. The sum-rate improvement attained ranges from 8 bps/Hz to 13 bps/Hz for various transmit powers at the base station (BS) and at the UEs, which is significant.
3.
Xiao, Yun; Wang, Enhao; Chen, Yunfei
Integrated Sensing and Communications With Multiple Targets and Multiple Users in Mixed Field Proceedings Article
In: 2024 IEEE 24th International Conference on Communication Technology (ICCT), pp. 1288–1292, 2024, ISSN: 2576-7828, (ISSN: 2576-7828).
Abstract | Links | BibTeX | Tags: Antenna arrays, Array signal processing, Beamforming, far-filed, Integrated sensing and communication, integrated sensing and communications, Interference, mixed field, model mismatch, multiple-target, near-field, Next generation networking, Numerical models, Optimization, Propagation losses, Signal to noise ratio, Wireless communication
@inproceedings{xiao_integrated_2024,
title = {Integrated Sensing and Communications With Multiple Targets and Multiple Users in Mixed Field},
author = {Yun Xiao and Enhao Wang and Yunfei Chen},
url = {https://ieeexplore.ieee.org/document/10946468},
doi = {10.1109/ICCT62411.2024.10946468},
issn = {2576-7828},
year = {2024},
date = {2024-10-01},
urldate = {2025-10-08},
booktitle = {2024 IEEE 24th International Conference on Communication Technology (ICCT)},
pages = {1288–1292},
abstract = {Integrated sensing and communications (ISAC) plays a crucial role in the next-generation wireless systems. Owing to the deployment of high carrier frequencies and/or large-scale antenna arrays, targets and communications users in the ISAC systems may follow different propagation models. However, most existing works assume the same propagation model for both communications and sensing. This work considers a practical scenario where multiple targets and communications users are in different fields. Beamforming design is proposed to optimize the sensing signal-to-clutter-plus-noise ratio (SCNR) of each target. Specifically, a sensing performance fairness profile optimization (FPO) problem is formulated, and a Dinkelbach-type algorithm is proposed to solve the problem. Numerical results show the tradeoff between mixed-field communications and sensing, the effects of antenna size and model mismatch between near field and far field on the sensing performance of the mixed-field ISAC.},
note = {ISSN: 2576-7828},
keywords = {Antenna arrays, Array signal processing, Beamforming, far-filed, Integrated sensing and communication, integrated sensing and communications, Interference, mixed field, model mismatch, multiple-target, near-field, Next generation networking, Numerical models, Optimization, Propagation losses, Signal to noise ratio, Wireless communication},
pubstate = {published},
tppubtype = {inproceedings}
}
Integrated sensing and communications (ISAC) plays a crucial role in the next-generation wireless systems. Owing to the deployment of high carrier frequencies and/or large-scale antenna arrays, targets and communications users in the ISAC systems may follow different propagation models. However, most existing works assume the same propagation model for both communications and sensing. This work considers a practical scenario where multiple targets and communications users are in different fields. Beamforming design is proposed to optimize the sensing signal-to-clutter-plus-noise ratio (SCNR) of each target. Specifically, a sensing performance fairness profile optimization (FPO) problem is formulated, and a Dinkelbach-type algorithm is proposed to solve the problem. Numerical results show the tradeoff between mixed-field communications and sensing, the effects of antenna size and model mismatch between near field and far field on the sensing performance of the mixed-field ISAC.