Design and Analysis of Multi-Band Microstrip Antenna with Optimization of Performance using Supported Vector Regression for Wireless Communication Systems
No Thumbnail Available
Date
2025-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
The increasing demand for compact, high-performance antennas capable of supporting mul-
tiple wireless communication standards has driven the development of multi-band microstrip
antennas. This thesis presents the design, simulation, and optimization of a multi-band mi-
crostrip patch antenna operating at 2.4 GHz, 3.5 GHz, and 5.3 GHz, targeting applications
in Wi-Fi and WLAN systems. The antenna structure is designed and analyzed using CST
Microwave Studio, leveraging its full-wave 3D electromagnetic solver to evaluate key perfor-
mance metrics including parameters like re ection coe cient (S11), gain, bandwidth, and
radiation characteristics.
To enhance the antenna's performance and reduce the design iteration cycle, Support Vec-
tor Regression (SVR), a supervised machine learning technique, is employed. SVR models
the nonlinear relationship between the antenna's geometric parameters and its performance
outcomes, enabling e cient prediction and optimization. A data set is generated through
parametric simulations in CST, and the SVR model is trained to predict return loss and
gain across the three target frequencies.
The optimized antenna design achieves improved impedance matching, gain enhance-
ment, and bandwidth control at all three frequency bands. The results demonstrate that
the integration of SVR into the antenna design work ow provides a robust, data-driven
approach to achieving multi-band performance with high e ciency, making it suitable for
next-generation wireless communication systems.
Description
Keywords
Microstrip Antenna, Multi-band Antenna, Support Vector Regression Model, Optimization.