Machine Learning Based High Gain Wireless Antenna Design Operating at 5.2GHz Frequency

Year 2022, Volume: 2 Issue: 2, 94 - 98, 26.12.2022

Ekrem Akar

Abstract

When it comes to 3G, 4G, and the latest technology 5G, the relevance of wireless communication is growing day by day in the digitalizing and developing globe. The increased usage of wireless communication has highlighted the necessity for wireless communication equipment. When previous elements failed to match the demands, the demand for a superior version arose. WLAN networks are one of the most extensively utilized types of wireless communication. The most crucial components for data flow in this system are antennas. To address the demands and make appropriate transfers, several studies have been conducted. The frequency of the planned antenna is 5.2 GHz. With the integration of machine learning, the prediction system has been activated. It is planned that multiband and wideband antenna designs will be developed to facilitate wireless communications in this vast frequency range. The major goal of this article is to build a single antenna that can operate across several frequency ranges rather than multiple antennas that operate at various frequencies. About 0.33 is reserved for forecasting. An analysis was made on 500 iterations of 3 parameters. The FR-4 substrate with a dielectric coefficient of 4.3 is utilized in this antenna design. Copper have been utilizing as the material for the ground and patch components. 5.2 GHz working frequency, the return loss is 31.24 dB, bandwidth range is 4.9-5.38, gain is 3.57 dB.

Keywords

Antenna Design, WLANs, Wireless, Machine Learning, Microstrip

Thanks

This study has been carried out using the laboratory facilities of İzmir Katip Celebi University Smart Factory Systems Application and Research Center (AFSUAM).

References

• [1] Montero-de-Paz, Javier, et al. "Compact modules for wireless communication systems in the E-band (71–76 GHz)." Journal of Infrared, Millimeter, and Terahertz Waves 34.3 (2013): 251-266.
• [2] Rymanov, V., Palandöken, M., Lutzmann, S., Bouhlal, B., Tekin, T., & Stöhr, A. (2012, September). Integrated photonic 71–76 GHz transmitter module employing high linearity double mushroom-type 1.55 μm waveguide photodiodes. In 2012 IEEE International Topical Meeting on Microwave Photonics (pp. 253-256). IEEE.
• [3] Palandöken, M., Rymanov, V., Stöhr, A., & Tekin, T. (2012, August). Compact metamaterial-based bias tee design for 1.55 μm waveguide-photodiode based 71–76GHz wireless transmitter. In Progress in Electromagnetics Research Symposium, PIERS..
• [4] Palandöken, M., & Sondas, A. (2014). Compact Metamaterial Based Bandstop Filter. Microwave Journal, 57(10). [5] BAYTÖRE, C., GÖÇEN, C., PALANDÖKEN, M., Kaya, A., & ZORAL, E. Y. (2019). Compact metal-plate slotted WLAN-WIMAX antenna design with USB Wi-Fi adapter application. Turkish Journal of Electrical Engineering & Computer Sciences, 27(6), 4403-4417.
• [6] Demırbas, G. & Akar, E. (2022). Design and Interpretation of Microstrip Patch Antenna Operating at 2.4GHz for Wireless WI-FI Application. Avrupa Bilim ve Teknoloji Dergisi , Ejosat Special Issue 2022 (ICAENS-1) , 672-675 . DOI: 10.31590/ejosat.1084151
• [7] Akar, E., Akdag, I., & Gocen, C. (2022). Wi-Fi Antenna Design For E-Health Kit Based Biotelemetry Module. ICONTECH INTERNATIONAL JOURNAL, 6(1), 63-67. https://doi.org/10.46291/ICONTECHvol6iss1pp63-67
• [8] Demirbas, G., Gocen, C., & Akdag, I. (2022). Micro-strip Patch 2.4 GHz Wi-Fi Antenna Design For WLAN 4G- 5G Application . ICONTECH INTERNATIONAL JOURNAL, 6(1), 68-72. https://doi.org/10.46291/ICONTECHvol6iss1pp68-72
• [9] Gocen, C., & Palandoken, M. (2021). Machine Learning Assisted Novel Microwave Sensor Design for Dielectric Parameter Characterization of Water-Ethanol Mixture. IEEE Sensors Journal.
• [10] Zhang, L., See, K. Y., Zhang, B., & Zhang, Y. P. (2012). Integration of dual-band monopole and microstrip grid array for single-chip tri-band application. IEEE transactions on antennas and propagation, 61(1), 439-443.
• [11] Wang, D., & Chan, C. H. (2015). Multiband antenna for WiFi and WiGig communications. IEEE antennas and wireless propagation letters, 15, 309-312.
• [12] Sun, X. L., Liu, L., Cheung, S. W., & Yuk, T. I. (2012). Dual-band antenna with compact radiator for 2.4/5.2/5.8 GHz WLAN applications. IEEE transactions on Antennas and Propagation, 60(12), 5924-5931.
• [13] Deng, J., Li, J., Zhao, L., & Guo, L. (2017). A dual-band inverted-F MIMO antenna with enhanced isolation for WLAN applications. IEEE Antennas and Wireless Propagation Letters, 16, 2270-2273.
• [14] Ding, Y. R., & Cheng, Y. J. (2019). A tri-band shared-aperture antenna for (2.4, 5.2) GHz Wi-Fi application with MIMO function and 60 GHz Wi-Gig application with beam-scanning function. IEEE Transactions on Antennas and Propagation, 68(3), 1973-1981.
• [15] Prado, D. R., López-Fernández, J. A., Arrebola, M., & Goussetis, G. (2018, September). Efficient shaped-beam reflectarray design using machine learning techniques. In 2018 48th European Microwave Conference (EuMC) (pp. 1545-1548). IEEE.
• [16] Tokan, N. T., & Gunes, F. (2008). Support vector characterisation of the microstrip antennas based on measurements. Progress In Electromagnetics Research B, 5, 49-61.
• [17] Silva, C. R., & Martins, S. R. (2013). An adaptive evolutionary algorithm for UWB microstrip antennas optimization using a machine learning technique. Microwave and Optical Technology Letters, 55(8), 1864-1868.
• [18] Liu, B., Aliakbarian, H., Ma, Z., Vandenbosch, G. A., Gielen, G., & Excell, P. (2013). An efficient method for antenna design optimization based on evolutionary computation and machine learning techniques. IEEE transactions on antennas and propagation, 62(1), 7-18.