Abstract

In this paper, an artificial intelligence (AI)–based optimizer for plasma antennas is proposed for use in future wireless communication systems. The proposed approach is based on a feedforward neural network (FFNN) with multiple architectural configurations to achieve optimal plasma antenna performance over the 1–10 GHz frequency range. The selected FFNN architecture employs two hidden layers, with 15 neurons in the first layer and 10 neurons in the second layer. Environmental assessment indicates stable operation within a temperature range of 280–320 K and relative humidity levels of 30–80%. The AI-empowered system achieves up to a 24.7% improvement in efficiency compared to conventional approaches, with a peak efficiency of 76.4%. Furthermore, the integration of a multiple-input multiple-output (MIMO) configuration enhances channel capacity by 47.3% for a 4 × 4 array. Comprehensive simulation results validate the effectiveness of the proposed method for fifth-generation (5G) and sixth-generation (6G) communication scenarios, demonstrating excellent return loss characteristics and strong environmental tolerance. Overall, the proposed approach addresses key challenges in plasma antenna design, including frequency-dependent optimization, environmental adaptability, and MIMO integration, thereby supporting emerging wireless network applications.

Keywords

Artificial intelligence optimization, Plasma antennas, Feedforward neural network, MIMO systems, 5G/6G communications, Environmental robustness.

Cite this article

Kadhim MA, Hamid HS, Aftan AO. AI-driven optimization and environmental impact analysis of plasma antennas for next-generation wireless communication systems. International Journal of Advanced Technology and Engineering Exploration. 2026;13(134):47-66. DOI : 10.19101/IJATEE.2025.121220493

References

[1] Yang HJ. Reconfigurable antennas based on microplasma as a time-varying dielectric or conductor. Doctoral Dissertation, Electrical & Computer Engineering, University of Illinois at Urbana-Champaign. 2019.

[2] Levchenko I, Xu S, Cherkun O, Baranov O, Bazaka K. Plasma meets metamaterials: three ways to advance space micropropulsion systems. Advances in Physics: X. 2021; 6(1):1-28.

[3] Jun L, Xe L. Implementation of machine learning and artificial intelligence methods in enhancing the efficiency of models of antennas in complicated conditions. National Journal of Antennas and Propagation. 2024; 6(2):17-25.

[4] Saunders SR, Aragón-zavala AA. Antennas and propagation for wireless communication systems. John Wiley & Sons; 2024.

[5] Saeidi T, Ismail I, Wen WP, Alhawari AR, Mohammadi A. Ultra‐wideband antennas for wireless communication applications. International Journal of Antennas and Propagation. 2019; 2019(1):1-25.

[6] Magarotto M, De CP, Mansutti G, Bosi FJ, Buris NE, Capobianco AD, et al. Numerical suite for gaseous plasma antennas simulation. IEEE Transactions on Plasma Science. 2020; 49(1):285-97.

[7] Omheni N, Koubaa H, Zarai F. Artificial intelligence for 5G and 6G networks: a taxonomy-based survey of applications, trends, and challenges. Technologies. 2025; 13(12):1-50.

[8] Shen LH, Feng KT, Hanzo L. Five facets of 6G: research challenges and opportunities. ACM Computing Surveys. 2023; 55(11):1-39.

[9] Kumar R, Bora D. Experimental study of parameters of a plasma antenna. Plasma Science and Technology. 2010; 12(5):592.

[10] Raj T, Mishra R, Kumar P, Kapoor A. Advances in MIMO antenna design for 5G: a comprehensive review. Sensors. 2023; 23(14):1-34.

[11] Ahmad I, Tan W, Ali Q, Sun H. Latest performance improvement strategies and techniques used in 5G antenna designing technology, a comprehensive study. Micromachines. 2022; 13(5):1-28.

[12] Sarker N, Podder P, Mondal MR, Shafin SS, Kamruzzaman J. Applications of machine learning and deep learning in antenna design, optimization, and selection: a review. IEEE Access. 2023; 11:103890-915.

[13] Koziel S, Pietrenko-dabrowska A, Leifsson L. Antenna optimization using machine learning with reduced-dimensionality surrogates. Scientific Reports. 2024; 14(1):1-21.

[14] Bhavani S, Raviteja B, Shanmuganantham T. Scarecrow‐shaped antenna optimization using machine learning algorithms. International Journal of Communication Systems. 2025; 38(5):e70028.

[15] Harshasri K, Pandeeswari R. Compact dual-band metamaterial antenna using deep neural network for next-generation wireless communication. Optik. 2025; 327:172311.

[16] Gajbhiye PA, Singh SP, Sharma MK. A comprehensive review of AI and machine learning techniques in antenna design optimization and measurement. Discover Electronics. 2025; 2(1):1-31.

[17] Magarotto M, Sadeghikia F, Schenato L, Rocco D, Santagiustina M, Galtarossa A, et al. Plasma antennas: a comprehensive review. IEEE Access. 2024; 12:80468-90.

[18] Anderson T. Plasma Antennas. Artech House; 2020.

[19] Zaino R, Ahmed VS, Alozn ME, Alhammadi A. Impact of weather on radio-frequency energy harvesting efficiency: review and future directions. In international conference on technology management, operations and decisions (ICTMOD) 2024 (pp. 1-7). IEEE.

[20] Lim NC, Yong L, Su HT, Chai AY, Vithanawasam CK, Then YL, et al. Review of temperature and humidity impacts on RF signals. In 13th international UNIMAS engineering conference (EnCon) 2020 (pp. 1-8). IEEE.

[21] Maciuk K, Olejarz G, Abdelhamid M, Bem A, Krawczyk K, Postek P, et al. Dependence of seasonal phenomena in coordinate time series on GNSS antenna mounting height. Advances in Geodesy and Geoinformation. 2025; 74(1):1-14.

[22] Jemaludin NH, Al-gburi AJ, Elabd RH, Saeidi T, Akbar MF, Ibrahim IM, et al. A comprehensive review on MIMO antennas for 5G smartphones: mutual coupling techniques, comparative studies, SAR analysis, and future directions. Results in Engineering. 2024; 23:102712.

[23] Upadhyay S, Pandian R, Subudhi AK, Boregowda VK, Mishra S, Taneja M, et al. Smart antennas for next-generation wireless networks. National Journal of Antennas and Propagation. 2025; 7(2):29-33.

[24] Esmail BA, Isleifson D, Koziel S. Dual-band millimetre wave MIMO antenna with reduced mutual coupling based on optimized parasitic structure and ground modification. Scientific Reports. 2024; 14(1):1-16.

[25] Koziel S, Abdullah M. Machine-learning-powered EM-based framework for efficient and reliable design of low scattering metasurfaces. IEEE Transactions on Microwave Theory and Techniques. 2021; 69(4):2028-41.

[26] Kwon H, Kim E, Cho S, Kwon DC, Choe HH, Choi M. Plasma-simulation physics informed neural networks (PS-PINNs) for global discharge models. East Asian Journal on Applied Mathematics. 2024; 14(3):636-56.

[27] Sadeghikia F, Horestani AK, Himdi M. Reconfigurable antennas based on plasma reflectors and cylindrical slotted waveguide. Plasma Science-Recent Advances, New Perspectives and Applications. 2022:1-28.