{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T10:08:39Z","timestamp":1788948519637,"version":"build-2803163510"},"reference-count":14,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301337"],"award-info":[{"award-number":["62301337"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["62301337"],"award-info":[{"award-number":["62301337"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012840","name":"Scientific Research Fund of Shenzhen Polytechnic University","doi-asserted-by":"publisher","award":["6024310032K"],"award-info":[{"award-number":["6024310032K"]}],"id":[{"id":"10.13039\/100012840","id-type":"DOI","asserted-by":"publisher"}]},{"award":["6024310032K"],"award-info":[{"award-number":["6024310032K"]}],"id":[{"id":"https:\/\/ror.org\/00d2w9g53","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Millimeter wave (mmWave) Massive MIMO is a cornerstone technology for sixth-generation (6G) wireless networks, providing the directional gain necessary to overcome high path loss. However, the acquisition of high-fidelity Channel State Information (CSI) and the associated beamforming overhead remain significant bottlenecks, particularly in dynamic environments with frequent blockages. In this paper, we propose a fast and robust beamforming strategy enabled by a digital twin (DT) framework. Specifically, we develop a Conditional Generative Adversarial Network (cGAN)-based DT module that serves as a high-fidelity virtual surrogate for site-specific ray-tracing. By processing environmental 3D geometry and dynamic obstacle data, the cGAN predicts real-time Beam-Power Maps (BPM) with minimal computational latency. Building upon these predictions, we introduce a Graph Neural Network (GNN)-based resource allocation agent that models the network as a spatial interference graph to perform coordination and power control. Numerical results demonstrate that our proposed DT-assisted approach significantly reduces online interaction overhead by shifting the computational burden of ray-tracing to an offline generative phase. Furthermore, the framework achieves superior sum-rate performance and link robustness under dynamic blockages compared to conventional deep learning and heuristic benchmarks.<\/jats:p>","DOI":"10.3390\/s26185715","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:24:02Z","timestamp":1788945842000},"page":"5715","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Digital Twin-Assisted Beamforming for Millimeter Wave Massive MIMO"],"prefix":"10.3390","volume":"26","author":[{"given":"Ke","family":"Xu","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, Shenzhen Polytechnic University, Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"given":"Weiqiang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Shenzhen Polytechnic University, Shenzhen 518055, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1109\/MCOM.2014.6979963","article-title":"MIMO Precoding and Combining Solutions for Millimeter-Wave Systems","volume":"52","author":"Alkhateeb","year":"2014","journal-title":"IEEE Commun. Mag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1109\/JSAC.2014.2328098","article-title":"What Will 5G Be?","volume":"32","author":"Andrews","year":"2014","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/JIOT.2019.2948888","article-title":"A Comprehensive Survey on Internet of Things (IoT) Toward 5G Wireless Systems","volume":"7","author":"Chettri","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1109\/COMST.2018.2869411","article-title":"A Tutorial on Beam Management for 3GPP NR at mmWave Frequencies","volume":"21","author":"Giordani","year":"2019","journal-title":"IEEE Commun. Surv. Tuts."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2317","DOI":"10.1109\/JSAC.2022.3180803","article-title":"Learning-Based Predictive Beamforming for Integrated Sensing and Communication in Vehicular Networks","volume":"40","author":"Liu","year":"2022","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2034","DOI":"10.1109\/TWC.2020.3038787","article-title":"Intelligent Interactive Beam Training for Millimeter Wave Communications","volume":"20","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1109\/JSTSP.2024.3405856","article-title":"Predictive Beamforming for Vehicles With Complex Behaviors in ISAC Systems: A Deep Learning Approach","volume":"18","author":"Zhang","year":"2024","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"9875","DOI":"10.1109\/TWC.2025.3650204","article-title":"Efficient Beam Selection for ISAC in Cell-Free Massive MIMO via Digital Twin-Assisted Deep Reinforcement Learning","volume":"25","author":"Zhang","year":"2026","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2435","DOI":"10.1109\/TWC.2025.3596804","article-title":"Digital Twin-Assisted Explainable AI for Robust Beam Prediction in mmWave MIMO Systems","volume":"25","author":"Khan","year":"2026","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_10","unstructured":"XG Mobile Forum (XGMF) (2026). Beyond 5G White Paper: AI and Digital Twin v2.0, XG Mobile Forum. White Paper."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1109\/TCOMM.2017.2771308","article-title":"Out-of-Band Millimeter Wave Beamforming and Communications to Achieve Low Latency and High Energy Efficiency in 5G Systems","volume":"66","author":"Hashemi","year":"2018","journal-title":"IEEE Trans. Commun."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1109\/TAP.2024.3472214","article-title":"Calibration of NYURay for Ray Tracing Using 28, 73, and 142 GHz Channel Measurements Conducted in Indoor, Outdoor, and Factory Scenarios","volume":"73","author":"Kanhere","year":"2025","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1109\/TVT.2021.3049380","article-title":"A Deep Learning-Based Low Overhead Beam Selection in mmWave Communications","volume":"70","author":"Echigo","year":"2021","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2922","DOI":"10.1109\/TIT.2023.3312134","article-title":"Maximizing Weighted Sum-Rate Over Gaussian Broadcast Channels","volume":"70","author":"Wan","year":"2024","journal-title":"IEEE Trans. Inf. Theory"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5715\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:33:00Z","timestamp":1788946380000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5715"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":14,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26185715"],"URL":"https:\/\/doi.org\/10.3390\/s26185715","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]}}}