Rancang Bangun Antena Mikrostrip Rectangular Patch Array 2x1 dengan Slot Rectangular pada Frekuensi 2.45 GHz Berbasis Machine Learning Random Forest

Abstract

The development of wireless communication technology demands devices capable of supporting efficient data transmission, one of which is the microstrip antenna. This type of antenna is well known for its compact shape, lightweight design, and ease of integration with modern systems. This research focuses on the design and optimization of a 2×1 rectangular patch microstrip antenna array with a rectangular slot operating at a frequency of 2.45 GHz. The optimization process utilizes the Random Forest machine learning algorithm to achieve more efficient and accurate antenna performance. Simulation results show an improvement in antenna performance parameters after optimization, with a gain of 4.67 dBi, bandwidth of 99.3 MHz, return loss of -19.63 dB, and a VSWR of 1.19. Experimental validation using a VNA confirms that the designed antenna operates effectively at 2.45 GHz and supports communication within the ISM frequency band. The machine learning-based approach proves to be effective in providing optimal and efficient antenna recommendations. This research is expected to serve as a reference for the development of smart antennas and as a learning module in the Intelligent Radio System Laboratory, Universitas Sumatera Utara.