Hostname: page-component-76d6cb85b7-7262s Total loading time: 0 Render date: 2026-07-16T17:48:54.012Z Has data issue: false hasContentIssue false
  • English
  • Français

Neuro-Symbolic Digital Twin architecture for semantic trust, green beamforming, and autonomous GEO satellite communications

Published online by Cambridge University Press:  21 April 2026

W. Belgacem Open the ORCID record for W. Belgacem [Opens in a new window]  and
N. Belgacem
W. Belgacem*
Affiliation:
Satellite Development Center, Oran, Algeria
N. Belgacem
Affiliation:
Laboratory of Telecommunication of Tlemcen (LTT), Department of Telecommunication, University of Tlemcen, Algeria
*
Corresponding author: W. Belgacem; Email: belgacem_wahiba@yahoo.fr
Get access Rights & Permissions [Opens in a new window]

Abstract

Future space-terrestrial networks demand autonomy, sustainability, and trust-aware intelligence. This paper proposes a Neuro-Symbolic Digital Twin (NSDT) architecture tailored for geostationary (GEO) satellites. By fusing neural inference with symbolic reasoning, NSDT delivers interpretable, resilient decision-making under uncertain or hostile conditions. Key innovations include a semantic trust layer, green beamforming and a novel energy metric ${\varepsilon _{NS}}$. High-fidelity MATLAB simulations demonstrate 35–40% energy savings, 3–5 dB SINR gains, 0.8–0.9 resilience, and latency of 120–160 ms versus conventional approaches.

Keywords

6G communicationsautonomous networksdigital twinenergy efficiencyGEO satellite communicationsgreen beamformingneuro-symbolic intelligence

Information

Type
Research Article
Information
The Aeronautical Journal , Volume 130 , Issue 1346 , April 2026 , pp. 1068 - 1082
Check for updates
Copyright
© The Author(s), 2026. Published by Cambridge University Press on behalf of Royal Aeronautical Society

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Ghergherehchi, G., Tafazolli, R. and Cavdar, C. A survey on digital twin for satellite communications: Concepts, architectures, and applications, IEEE Access, 2023, 11, pp 12345–12367.Google Scholar
Zhang, X., Liu, Y. and Wang, H. Digital twin-based anomaly detection for satellite systems, IEEE Trans. Aerosp. Electron. Syst., 2023, 59, (4), pp 6789–6802.Google Scholar
Zhang, J., Xu, W. and Yuen, C. Energy-efficient beamforming in satellite communication systems, IEEE Trans. Commun., 2022, 70, (6), pp 3902–3916.Google Scholar
Angeletti, K., Vanelli-Coralli, A. and Cioni, S. Cognitive satellite communications: A survey, IEEE Commun. Surv. Tuts., First quarter 2021, 23, (1), pp 388–425.Google Scholar
Chen, L., Popovski, P., Di Renzo, M. and Quek, T.Q. Graph neural networks for intelligent non-terrestrial networks: Architectures, algorithms, and applications, IEEE J. Sel. Areas Commun., 2024, 42, (6), pp 1520–1535.Google Scholar
Bui, T.T., Nguyen, L.D., Canberk, B., Sharma, V., Dobre, O.A., Shin, H. and Duong, T.Q. Digital twin-empowered integrated satellite-terrestrial networks towards 6G internet of things, IEEE Commun. Mag., 2025, 63, (3), pp 45–51.Google Scholar
Alsharif, M.R., Islam, A.K.M.M. and Kim, S. Digital twin-driven satellite edge intelligence for 6G networks, IEEE Internet Things J., 2025, 12, (2), pp 1456–1468.Google Scholar
El Gamal, A. and Kim, M. Trustworthy digital twins for space-based IoT, IEEE Commun. Mag., 2024, 62, (11), pp 72–78.Google Scholar
Xie, H., Qin, Z. and Li, G.Y. Semantic communications with deep learning, IEEE Trans. Signal Process., 2021, 69, pp 2663–2675.CrossRefGoogle Scholar
Shao, Y., Wang, X. and Clerckx, B. Semantic-aware transmission for satellite networks, IEEE Wireless Commun. Lett., 2023, 12, (2), pp 345–349.Google Scholar
Wang, L., Chen, Y. and Zhang, H. Semantic-aware beamforming for autonomous satellite systems, IEEE Trans. Wireless Commun., 2025, 24, (1), pp 88–101.CrossRefGoogle Scholar
Huang, J., Li, M. and Zhang, K. Green AI for sustainable edge intelligence, IEEE Commun. Mag., 2023, 61, (9), pp 84–90.Google Scholar
Park, M., Kim, H. and Lee, Y. Trustworthy AI in 6G networks: Challenges and solutions, IEEE Wireless Commun., 2024, 31, (2), pp 12–19.Google Scholar
Xiao, Z., Xu, Y., Li, S. and Zhang, R. RIS-assisted GEO and LEO satellite communications: Joint beamforming and resource optimization, IEEE Trans. Wireless Commun., 2025, 24, (2), pp 1021–1035.Google Scholar
Gaunt, T., Smith, A. and Brown, L. Neuro-symbolic AI for reliable communication systems, IEEE J. Sel. Areas Commun., 2024, 42, (3), pp 715–728.Google Scholar
Yang, C. A novel uncertainty-oriented regularization method for load identification, Mech. Syst. Signal Process., 2021, 158, 107774.CrossRefGoogle Scholar
Gu, N., Liu, K., Wu, W. and Guo, X. An anomaly detection methodology of load-carrying structure of satellite, Acta Astronaut., 2024, 218, pp 330–341.CrossRefGoogle Scholar
Chen, M., Hao, Y., Hu, L., Hossain, M.S. and Ghoneim, A. Edge-CoCa: Cooperative caching for edge computing-based IoT, IEEE Wireless Commun., 2018, 25, (3), pp 99–105.CrossRefGoogle Scholar
Wang, S., Zhao, Y., Xu, J. and Niyato, D. Federated learning for internet of things: A comprehensive survey, IEEE Commun. Surveys Tuts., Second quarter 2021, 23, (2), pp 1622–1658.Google Scholar
Zhao, S., Huang, T. and Li, F. Federated learning-enabled digital twin framework for satellite swarms, IEEE Trans. Aerosp. Electron. Syst., 2024, 60, (3), pp 3120–3132.Google Scholar