1.
Li, Haiyuan; Li, Peizheng; Assis, Karcuis; Ullauri, Juan Marcelo Parra; Aijaz, Adnan; Yan, Shuangyi; Simeonidou, Dimitra
NetMind+: Adaptive Baseband Function Placement with GCN Encoding and Incremental Maze-solving DRL for Dynamic and Heterogeneous RANs Journal Article
In: IEEE Transactions on Network and Service Management, vol. 22, no. 4, pp. 3419–3432, 2025, ISSN: 1932-4537.
Abstract | Links | BibTeX | Tags: Advanced RAN, deep reinforcement learning, graph neural network, Incremental learning, MEC, Topology variation
@article{li_netmind_2025,
title = {NetMind+: Adaptive Baseband Function Placement with GCN Encoding and Incremental Maze-solving DRL for Dynamic and Heterogeneous RANs},
author = {Haiyuan Li and Peizheng Li and Karcuis Assis and Juan Marcelo Parra Ullauri and Adnan Aijaz and Shuangyi Yan and Dimitra Simeonidou},
doi = {10.1109/TNSM.2025.3570490},
issn = {1932-4537},
year = {2025},
date = {2025-08-01},
journal = {IEEE Transactions on Network and Service Management},
volume = {22},
number = {4},
pages = {3419–3432},
abstract = {The disaggregated architecture of advanced Radio Access Networks (RANs) with diverse X-haul latencies, in conjunction with resource-limited multi-access edge computing networks, presents significant challenges in designing a general model in placing baseband and user plane functions to accommodate versatile 5G services. This paper proposes a novel approach, NetMind+, which leverages Deep Reinforcement Learning (DRL) to determine the function placement strategies in diverse and evolving RAN topologies, aiming at minimizing power consumption. NetMind+ resolves the problem with a maze-solving strategy, enabling a Markov Decision Process with standardized action space scales across different networks. Additionally, a Graph Convolutional Network (GCN) based encoding and an incremental learning mechanism are introduced, allowing features from different and dynamic networks to be aggregated into a single DRL agent. This facilitates the generalization capability of DRL and minimizes the negative retraining impact. In an example with three sub-networks, NetMind+ demonstrates a substantial 32.76% improvement in power savings and a 41.67% increase in service stability compared to benchmarks from the existing literature. Compared to traditional methods necessitating a dedicated DRL agent for each network, NetMind+ attains comparable performance with 70% of the training cost savings. Furthermore, it demonstrates robust adaptability during network variations, accelerating training speed by 50%.},
keywords = {Advanced RAN, deep reinforcement learning, graph neural network, Incremental learning, MEC, Topology variation},
pubstate = {published},
tppubtype = {article}
}
The disaggregated architecture of advanced Radio Access Networks (RANs) with diverse X-haul latencies, in conjunction with resource-limited multi-access edge computing networks, presents significant challenges in designing a general model in placing baseband and user plane functions to accommodate versatile 5G services. This paper proposes a novel approach, NetMind+, which leverages Deep Reinforcement Learning (DRL) to determine the function placement strategies in diverse and evolving RAN topologies, aiming at minimizing power consumption. NetMind+ resolves the problem with a maze-solving strategy, enabling a Markov Decision Process with standardized action space scales across different networks. Additionally, a Graph Convolutional Network (GCN) based encoding and an incremental learning mechanism are introduced, allowing features from different and dynamic networks to be aggregated into a single DRL agent. This facilitates the generalization capability of DRL and minimizes the negative retraining impact. In an example with three sub-networks, NetMind+ demonstrates a substantial 32.76% improvement in power savings and a 41.67% increase in service stability compared to benchmarks from the existing literature. Compared to traditional methods necessitating a dedicated DRL agent for each network, NetMind+ attains comparable performance with 70% of the training cost savings. Furthermore, it demonstrates robust adaptability during network variations, accelerating training speed by 50%.
2.
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.