Modeling millimeter wave channels with generative adversarial networks

Yahia Ahmed Zakaria

doi:10.3103/S0735272724010035

Authors

Yahia Ahmed Zakaria National Research Centre, Cairo, Egypt https://orcid.org/0000-0002-0524-1802

DOI:

https://doi.org/10.3103/S0735272724010035

Keywords:

millimeter wave, subterahertz, neural networks, channel modelling

Abstract

Modern cellular systems increasingly rely on concurrent communication across several discontinuous bands due to broader bandwidth and macro-diversity. Multi-frequency communication is crucial in millimeter wave (mmWave) and terahertz (THz) frequencies, frequently paired with lower frequencies for resilience. Statistical models capable of representing the combined distribution of channel routes over many frequencies are needed to assess these systems. This research presents a broad neural network-based training approach for multi-frequency double-directional statistical channel models. The suggested method involves representing every channel as a multi-clustered set and training a generative adversarial network (GAN) to generate random multi-cluster profiles. The resulting cluster data consists of vectors distributed at various frequencies with random received powers, angles, and delays. Urban micro-cellular connections at 28 and 140 GHz are modeled using ray tracing data to demonstrate the methodology. The model is readily adaptable for multi-frequency link or network layer simulation. As studies show, the model may capture intriguing statistical correlations between frequencies, and the technique involves minimal statistical assumptions.

Author Biography

Yahia Ahmed Zakaria, National Research Centre, Cairo

Systems and Information Department, Engineering Research Institute for New and Renewable Energy

References

W. Xia et al., “Millimeter wave channel modeling via generative neural networks,” in 2020 IEEE Globecom Workshops (GC Wkshps, 2020, pp. 1–6, doi: https://doi.org/10.1109/GCWkshps50303.2020.9367420.

V. Degli-Esposti, F. Fuschini, E. M. Vitucci, G. Falciasecca, “Measurement and modelling of scattering from buildings,” IEEE Trans. Antennas Propag., vol. 55, no. 1, pp. 143–153, 2007, doi: https://doi.org/10.1109/TAP.2006.888422.

Y. A. Zakaria, E. K. I. Hamad, A. S. Abd Elhamid, K. M. El-Khatib, “Propagation measurements and calculation of path loss exponent for outdoor cellular communication systems at 3.5 GHz,” Radioelectron. Commun. Syst., vol. 64, no. 5, pp. 247–254, 2021, doi: https://doi.org/10.3103/S0735272721050034.

Y. Xing, T. S. Rappaport, “Millimeter wave and terahertz urban microcell propagation measurements and models,” IEEE Commun. Lett., vol. 25, no. 12, pp. 3755–3759, 2021, doi: https://doi.org/10.1109/LCOMM.2021.3117900.

J. Huang, C.-X. Wang, H. Chang, J. Sun, X. Gao, “Multi-frequency multi-scenario millimeter wave MIMO channel measurements and modeling for B5G wireless communication systems,” IEEE J. Sel. Areas Commun., vol. 38, no. 9, pp. 2010–2025, 2020, doi: https://doi.org/10.1109/JSAC.2020.3000839.

Y. Zakaria, L. Ivanek, “Propagation measurements and estimation of channel propagation models in urban environment,” KSII Trans. Internet Inf. Syst., vol. 11, no. 5, pp. 2453–2467, 2017, doi: https://doi.org/10.3837/tiis.2017.05.008.

W. Khawaja, O. Ozdemir, I. Guvenc, “UAV air-to-ground channel characterization for mmWave systems,” in 2017 IEEE 86th Vehicular Technology Conference (VTC-Fall), 2017, pp. 1–5, doi: https://doi.org/10.1109/VTCFall.2017.8288376.

O. Falade, “Deepmimo: a generic deep learning dataset for millimeter wave and massive mimo applications to vehicular communications,” SSRN Electron. J., 2023, doi: https://doi.org/10.2139/ssrn.4383745.

Remcom, “Electromagnetic Simulation Software.” https://www.remcom.com/.

R. He et al., “Clustering enabled wireless channel modeling using big data algorithms,” IEEE Commun. Mag., vol. 56, no. 5, pp. 177–183, 2018, doi: https://doi.org/10.1109/MCOM.2018.1700701.

A. Templeton, “Towards monosemanticity: decomposing language models with dictionary learning,” Transformer Circuits Thread, 2023. https://transformer-circuits.pub/2023/monosemantic-features/index.html.

A. Templeton, “Scaling monosemanticity: extracting interpretable features from claude 3 sonnet,” Transformer Circuits Thread, 2024. https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html.

“Mapping the mind of a large language model,” Web-site, 2024. https://www.anthropic.com/news/mapping-mind-language-model.

M. Shafi et al., “5G: A tutorial overview of standards, trials, challenges, deployment, and practice,” IEEE J. Sel. Areas Commun., vol. 35, no. 6, pp. 1201–1221, 2017, doi: https://doi.org/10.1109/JSAC.2017.2692307.

M. Giordani, M. Polese, M. Mezzavilla, S. Rangan, M. Zorzi, “Toward 6G networks: use cases and technologies,” IEEE Commun. Mag., vol. 58, no. 3, pp. 55–61, 2020, doi: https://doi.org/10.1109/MCOM.001.1900411.

T. S. Rappaport et al., “Wireless communications and applications above 100 GHz: Opportunities and challenges for 6G and beyond,” IEEE Access, vol. 7, pp. 78729–78757, 2019, doi: https://doi.org/10.1109/ACCESS.2019.2921522.

P. J. Rousseeuw, “Silhouettes: A graphical aid to the interpretation and validation of cluster analysis,” J. Comput. Appl. Math., vol. 20, pp. 53–65, 1987, doi: https://doi.org/10.1016/0377-0427(87)90125-7.

I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, A. Courville, “Improved training of wasserstein GANs,” in NIPS’17: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017, pp. 5769–5779, doi: https://doi.org/10.5555/3295222.3295327.

M. Arjovsky, S. Chintala, L. Bottou, “Wasserstein generative adversarial networks,” in Proceedings of the 34th International Conference on Machine Learning, 2017, pp. 214–223, uri: https://proceedings.mlr.press/v70/arjovsky17a.html.

I. GitHub, “Multi-freqeuncy millimeter wave channel modeling via generative adversarial network,” Web-site, 2021. https://github.com/klmyyaqihu/mmwchanmod-GAN.