Digital Twin-Based Ray Tracing Analysis for Antenna Orientation Optimization in Wireless Networks
Abstract
1. Introduction
2. Materials and Methods
2.1. Sionna
2.2. Workflow of the Proposed Framework
2.3. Ray Tracing Scenario Setup
2.4. Machine Learning Models
2.4.1. Model Selection
2.4.2. Model Architectures and Hyperparameters
2.4.3. Training, Validation, and Evaluation
3. Results
3.1. Ray Tracing-Based Performance Analysis
3.2. Performance Comparison of Machine Learning Models
3.3. Benchmarking Against Conventional Optimization Methods
4. Discussion
5. Conclusions
Funding
Data Availability Statement
Conflicts of Interest
References
- Li, L.; Sun, H.; Wang, Z.; Wang, W.; Fan, W. Digital Twins of Electromagnetic Propagation Environments for Live 5G Networks–Part I: Channel Acquisition, EM Simulation and Verification. IEEE Trans. Antennas Propag. 2024, 73, 2053–2064. [Google Scholar] [CrossRef]
- Gargari, A.A.; Pagin, M.; Polese, M.; Zorzi, M. 6G Integrated Access and Backhaul Networks with Sub-Terahertz Links. In Proceedings of the 2023 18th Wireless On-Demand Network Systems and Services Conference (WONS), Madonna di Campiglio, Italy, 30 January–1 February 2023; IEEE: New York, NY, USA; pp. 13–19. [Google Scholar]
- Hoydis, J.; Cammerer, S.; Aoudia, F.A.; Vem, A.; Binder, N.; Marcus, G.; Keller, A. Sionna: An Open-Source Library for Next-Generation Physical Layer Research. arXiv 2023, arXiv:2203.11854. [Google Scholar] [CrossRef]
- Hoydis, J.; Aoudia, F.A.; Cammerer, S.; Nimier-David, M.; Binder, N.; Marcus, G.; Keller, A. Sionna RT: Differentiable Ray Tracing for Radio Propagation Modeling. In Proceedings of the 2023 IEEE Globecom Workshops (GC Wkshps), Kuala Lumpur, Malaysia, 4–8 December 2023; IEEE: New York, NY, USA, 2023; pp. 317–321. [Google Scholar]
- Xia, G.; Zhou, C.; Zhang, F.; Cui, Z.; Liu, C.; Ji, H.; Zhang, X.; Zhao, Z.; Xiao, Y. Path Loss Prediction in Urban Environments with Sionna-RT Based on Accurate Propagation Scene Models At 2.8 GHz. IEEE Trans. Antennas Propag. 2024, 72, 7986–7997. [Google Scholar] [CrossRef]
- Zubow, A.; Pilz, Y.; Rösler, S.; Dressler, F. Ns3 Meets Sionna: Using Realistic Channels in Network Simulation. arXiv 2024, arXiv:2412.20524. [Google Scholar] [CrossRef]
- Zhu, M.; Cazzella, L.; Linsalata, F.; Magarini, M.; Matteucci, M.; Spagnolini, U. On the Digitization of the EM Environment: A Comparison of Ray Launching Solutions. In Proceedings of the 2024 IEEE International Mediterranean Conference on Communications and Networking (MeditCom), Madrid, Spain, 8–11 July 2024; IEEE: New York, NY, USA, 2024; pp. 85–90. [Google Scholar]
- Pegurri, R.; Linsalata, F.; Moro, E.; Hoydis, J.; Spagnolini, U. Toward Digital Network Twins: Integrating Sionna RT in ns-3 for 6G Multi-RAT Networks Simulations. arXiv 2025, arXiv:2501.00372. [Google Scholar] [CrossRef]
- Hoydis, J.; Aït Aoudia, F.; Cammerer, S.; Euchner, F.; Nimier-David, M.; Ten Brink, S.; Keller, A. Learning Radio Environments by Differentiable Ray Tracing. IEEE Trans. Mach. Learn. Commun. Netw. 2024, 2, 1527–1539. [Google Scholar] [CrossRef]
- Amatare, S.; Singh, G.; Samson, M.; Roy, D. RagNAR: Ray-Tracing Based Navigation for Autonomous Robot in Unstructured Environment. 2024. Available online: https://ieeexplore.ieee.org/document/10901133 (accessed on 26 April 2025).
- Amatare, S.; Samson, M.; Roy, D. Testbed Design for Robot Navigation Through Differential Ray Tracing. In Proceedings of the 2024 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), Washington, DC, USA, 13–16 May 2024; IEEE: New York, NY, USA, 2024; pp. 173–174. [Google Scholar]
- Aram, M.G.; Guo, H.; Yin, M.; Svensson, T. Site-Specific Outdoor Propagation Assessment and Ray-Tracing Analysis for Wireless Digital Twins. In Proceedings of the 2025 19th European Conference on Antennas and Propagation (EuCAP), Stockholm, Sweden, 30 March–4 April 2025; IEEE: New York, NY, USA, 2025; pp. 1–5. [Google Scholar]
- Testolina, P.; Polese, M.; Johari, P.; Melodia, T. Boston Twin: The Boston Digital Twin for Ray-Tracing in 6G Networks. In Proceedings of the ACM Multimedia Systems Conference 2024 on ZZZ, Bari, Italy, 15–18 April 2024; ACM: Bari, Italy, 2024; pp. 441–447. [Google Scholar]
- Noh, Y.J.; Choi, K.W. High-Precision Digital Twin Platform Based on Ray Tracing Simulation. In Proceedings of the 2024 15th International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island, Republic of Korea, 14 January 2025; IEEE: New York, NY, USA, 2024; pp. 1464–1465. [Google Scholar]
- Zhao, L.; Li, S.; Guan, Y.; Wan, S.; Hawbani, A.; Bi, Y.; Guizani, M. Adaptive Multi-UAV Trajectory Planning Leveraging Digital Twin Technology for Urban IIoT Applications. IEEE Trans. Netw. Sci. Eng. 2023, 11, 5349–5363. [Google Scholar] [CrossRef]
- Wu, M.; Xiao, Y.; Gao, Y.; Xiao, M. Digital Twin for UAV-RIS Assisted Vehicular Communication Systems. IEEE Trans. Wirel. Commun. 2023, 23, 7638–7651. [Google Scholar] [CrossRef]
- Lee, J.-H.; Molisch, A.F. AutoBS: Autonomous Base Station Deployment Framework with Reinforcement Learning and Digital Twin Network. arXiv 2025, arXiv:2502.19647. [Google Scholar]
- Lee, J.-H.; Serbetci, O.G.; Selvam, D.P.; Molisch, A.F. PMNet: Robust Pathloss Map Prediction via Supervised Learning. In Proceedings of the GLOBECOM 2023-2023 IEEE Global Communications Conference, Kuala Lumpur, Malaysia, 4–8 December 2023; IEEE: New York, NY, USA, 2023; pp. 4601–4606. [Google Scholar]
- He, D.; Guan, K.; Yan, D.; Yi, H.; Zhang, Z.; Wang, X.; Zhong, Z.; Zorba, N. Physics and AI-Based Digital Twin of Multi-Spectrum Propagation Characteristics for Communication and Sensing in 6G and Beyond. IEEE J. Sel. Areas Commun. 2023, 41, 3461–3473. [Google Scholar] [CrossRef]
- Aït Aoudia, F.; Hoydis, J.; Cammerer, S.; Van Keirsbilck, M.; Keller, A. Deep Learning-Based Synchronization for Uplink NB-IoT. In Proceedings of the GLOBECOM 2022-2022 IEEE Global Communications Conference, Rio de Janeiro, Brazil, 11 January 2023; IEEE: New York, NY, USA, 2022; pp. 1478–1483. [Google Scholar]
- Wiesmayr, R.; Cammerer, S.; Aoudia, F.A.; Hoydis, J.; Zakrzewski, J.; Keller, A. Design of a Standard-Compliant Real-Time Neural Receiver for 5G NR. arXiv 2024, arXiv:2409.02912. [Google Scholar] [CrossRef]
- Cammerer, S.; Hoydis, J.; Aït Aoudia, F.; Keller, A. Graph Neural Networks for Channel Decoding. In Proceedings of the 2022 IEEE Globecom Workshops (GC Wkshps), Rio de Janeiro, Brazil, 4–8 December 2022; IEEE: New York, NY, USA, 2022; pp. 486–491. [Google Scholar]
- Lee, J.-H.; Lee, D.-H.; Lee, J.; Pujara, J. Integrating Pre-Trained Language Model with Physical Layer Communications. IEEE Trans. Wirel. Commun. 2024, 23, 17266–17278. [Google Scholar] [CrossRef]
- Raza, W.; Khan, F.A.; Qureshi, H.N.; Masood, U.; Imran, A. An AI-Driven Framework for Enhancing Resilience in Propagation Models to Enable Digital Twin. In Proceedings of the 2024 IEEE 35th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), Valencia, Spain, 2–5 September 2024; IEEE: New York, NY, USA, 2024; pp. 1–6. [Google Scholar]
- Sucuoglu, H.S. Development of Real-Time Fire Detection Robotic System with Hybrid-Cascade Machine Learning Detection Structure. Processes 2025, 13, 1712. [Google Scholar] [CrossRef]
- Jakob, W.; Speierer, S.; Roussel, N.; Vicini, D. JIT: A Just-in-Time Compiler for Differentiable Rendering. ACM Trans. Graph. 2022, 41, 1–19. [Google Scholar] [CrossRef]
- Martín, A.; Ashish, A.; Paul, B.; Eugene, B.; Zhifeng, C.; Craig, C.; Greg, S.C.; Andy, D.; Jeffrey, D.; Matthieu, D. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. arXiv 2015, arXiv:1603.04467. [Google Scholar]
- Blender Foundation Blender. Available online: https://www.blender.org (accessed on 15 December 2024).
- Jakob, W.; Speierer, S.; Roussel, N.; Nimier-David, M.; Vicini, D.; Zeltner, T.; Nicolet, B.; Crespo, M.; Leroy, V.; Zhang, Z. Mitsuba 3 Physically Based Renderer 2022. Available online: https://www.mitsuba-renderer.org/ (accessed on 2 February 2025).
- Prochitecture Blender-OSM: OpenStreetMap and Terrain for Blender. Available online: https://prochitecture.gumroad.com/l/blender-osm (accessed on 15 December 2024).
- OpenStreetMap Foundation OpenStreetMap. Available online: https://www.openstreetmap.org (accessed on 10 December 2024).
- ITU–R. P.2040–3 Effects of Building Materials and Structures on Radiowave Propagation Above About 100 MHz. 2023. Available online: https://www.itu.int/rec/R-REC-P.2040/en (accessed on 3 February 2025).
- Tikaria, M.; Nigam, V.S. Ultrahigh Frequency Path Loss Prediction Based on K-Nearest Neighbors. Int. J. Microw. Wirel. Technol. 2024, 16, 990–1000. [Google Scholar] [CrossRef]
- Singh, H.; Gupta, S.; Dhawan, C.; Mishra, A. Path Loss Prediction in Smart Campus Environment: Machine Learning-Based Approaches. In Proceedings of the 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Antwerp, Belgium, 25–28 May 2020; IEEE: New York, NY, USA, 2020; pp. 1–5. [Google Scholar]
- Mongi, B.E.N.; Jalel, C.; Mohamed Hadi, H.; Jamel, B.H.T. Machine Learning for Improved Path Loss Prediction in Urban Vehicle-to-Infrastructure Communication Systems. Front. Artif. Intell. 2025, 8, 1597981. [Google Scholar]
- Bernstein, D.J. Understanding Brute Force. Workshop Record of ECRYPT STVL Workshop on Symmetric Key Encryption, ESTREAM Report. Available online: https://cr.yp.to/snuffle/bruteforce-20050425.pdf (accessed on 2 May 2025).
- Borst, S.; Saniee, I.; Silva, A.; Whiting, P. Self-Learning Algorithms for KPI Optimization in Wireless Cellular Networks. 2010. Available online: https://www.researchgate.net/publication/266184374_Self-Learning_Algorithms_for_KPI_Optimization_in_Wireless_Cellular_Networks (accessed on 2 May 2025).
Material Class | Real Part of Relative Permittivity | Conductivity [S/m] | Frequency Range (GHz) | ||
---|---|---|---|---|---|
A | b | C | d | ||
Concrete | 5.24 | 0 | 0.0462 | 0.7822 | 1–100 |
Brick | 3.91 | 0 | 0.0238 | 0.16 | 1–40 |
Metal | 1 | 0 | 107 | 0 | 1–100 |
Ground 1 | 15 | −0.1 | 0.035 | 1.63 | 1–10 |
Parameter | Value |
---|---|
Frequency | 3.5 GHz |
Number of transmitters | 3 |
Transmitter height | 30 m |
Transmitter power | 44 dBm |
Transmitter array type | Planar array (8 × 2) |
Transmitter array pattern | TR 38.901 standard |
Number of users | 60 |
User distribution | Uniform |
Receiver array type | Planar array (1 × 1) |
Receiver array pattern | Dipole |
Number of reflections | 3 |
Resolution for rendering | [1000, 600] |
Category | Model | Representative Evidence | Intended Role |
---|---|---|---|
Lightweight | K-Nearest Neighbors (KNN) | Outdoor UHF studies have reported <3 dB RMSE when k ≤ 11 [33] | Fast, interpretable lower bound |
Intermediate | Multi-Layer Perceptron (MLP) | Campus-scale analyses have shown 25–30% error reduction over linear baselines [34] | Flexible capture of moderate nonlinearity |
State-of-the-art | Extreme Gradient Boosting (XGBoost) | 3.5 GHz urban trials have yielded the lowest MAE/RMSE among tree-based models [35] | Highest accuracy and built-in explainability |
Model | Feature Scaling | Key Settings |
---|---|---|
KNN | StandardScaler | n_neighbors = 7; weights = ‘distance’; metric = ‘euclidean’ |
MLP | StandardScaler → MLP | Hidden layers = [128, 64, 32], activation = ReLU; optimizer = Adam (lr = 1 × 10−3); batch_size = 64; L2 = 1 × 10−4; max_iter = 1000; early_stopping = True |
XGBoost | Raw features | n_estimators = 600; learning_rate = 0.9; max_depth = 6; subsample = 0.8; colsample_bytree = 0.8; reg_lambda = 2; tree_method = ‘hist’ |
Category | Min [dB] | Max [dB] | Mean [dB] |
---|---|---|---|
Experimental Results | −174.18 | −73.13 | −95.76 |
KNN | −178.94 | −73.66 | −99.96 |
MLP | −175.29 | −73.71 | −105.59 |
XGBoost | −173.08 | −74.13 | −94.87 |
Category | Min [dBm] | Max [dBm] | Mean [dBm] |
---|---|---|---|
Experimental Results | −130.18 | −29.13 | −51.76 |
KNN | −131.83 | −29.86 | −54.26 |
MLP | −123.41 | −30.06 | −55.97 |
XGBoost | −135.16 | −29.60 | −54.20 |
Category | Min [dB] | Max [dB] | Mean [dB] |
---|---|---|---|
Experimental Results | −30.14 | 85.10 | 35.60 |
KNN | −21.32 | 83.33 | 28.64 |
MLP | −21.77 | 83.55 | 30.56 |
XGBoost | −20.98 | 83.52 | 36.75 |
Performance Metrics | Output | ML Algorithm | ||
---|---|---|---|---|
KNN | MLP | XGBoost | ||
Path gain | MSE | 1.5333 | 2.3811 | 0.4483 |
R2 | 0.554 | −0.0754 | 0.9618 | |
RSS | MSE | 1.5333 | 2.3811 | 0.4483 |
R2 | 0.554 | −0.0754 | 0.9618 | |
SINR | MSE | 1.7528 | 1.8615 | 0.5215 |
R2 | 0.3008 | 0.2114 | 0.9381 |
Model | Training Time (s) (CPU) | Hyperparameter Search (s) (CV) | Total ML Time (s) | Inference per Link (ms) |
---|---|---|---|---|
KNN | - | 0.44 | 0.44 | 0.23 |
MLP | 4.60 | 0.62 | 5.22 | 0.14 |
XGBoost | 1.24 | 0.45 | 1.76 | 0.08 |
Method | Median SINR (dB) | Runtime |
---|---|---|
Exhaustive Search | 32.38 | 10 h |
KPI-Driven Hill-Climb | 21 | 6 min |
XGBoost | 35.70 | 1.76 s |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yildiz, O. Digital Twin-Based Ray Tracing Analysis for Antenna Orientation Optimization in Wireless Networks. Electronics 2025, 14, 3023. https://doi.org/10.3390/electronics14153023
Yildiz O. Digital Twin-Based Ray Tracing Analysis for Antenna Orientation Optimization in Wireless Networks. Electronics. 2025; 14(15):3023. https://doi.org/10.3390/electronics14153023
Chicago/Turabian StyleYildiz, Onem. 2025. "Digital Twin-Based Ray Tracing Analysis for Antenna Orientation Optimization in Wireless Networks" Electronics 14, no. 15: 3023. https://doi.org/10.3390/electronics14153023
APA StyleYildiz, O. (2025). Digital Twin-Based Ray Tracing Analysis for Antenna Orientation Optimization in Wireless Networks. Electronics, 14(15), 3023. https://doi.org/10.3390/electronics14153023