Machine learning driven four-elements high gain MIMO antenna for wireless connectivity

Abstract

With innovative technologies developing at a rapid pace, machine learning has become essential to improve interdisciplinary applications such as wireless communications systems. In order to optimize, design and develop a compact (0.6λ×0.6λ×0.03λmm3) four-elements MIMO antenna at 2.4 GHz resonating frequency, this study uses a machine learning technique. A single element antenna is selected among several steps (1–4) and thereafter, an antenna (A3) turns out to be the best option out of the antennas that were taken into consideration (A1–A3). The optimal antenna (A3) dimensions were carefully ascertained by means of a thorough investigation of 245,700 distinct iterations. The proposed antenna consists of a petal-shaped structure on the center of the radiating plane and rectangular ring with defected semicircles on the ground plane. The antenna exhibits 72.3% (simulated) and 70.2% (measured) impedance bandwidth with a high value of 20 dB of isolation (at 3 GHz). The suggested antenna achieves a maximum gain and radiation efficiency of 9.2 dB and 80% at 2.1 GHz, respectively. Moreover, MIMO characteristics such as Envelope Correlation Coefficient (ECC), Total Active Reflection Coefficient (TARC) and Channel Capacity Loss (CCL) of the intended antenna are studied and found to be well within acceptable limits. The suggested antenna is analysed by means of EM simulator high-frequency structure simulator (HFSS), thereafter it is fabricated and measured and findings show a fair degree of agreement. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.