Design and Development of Graphene Patch Antenna Using Metasurface: Hybrid Optimization Model for Optimal Tuning of Antenna Components

The operational communication system anticipates reaching data speeds of hundreds of gigabits per second. Because of its unique mechanical and electrical characteristics, meta surface (MTS) containing graphene has become viable option for meeting these requirements. The purpose of this study is to show design of reconfigurable antenna operating over Terahertz (THz) band that is efficient due to graphene. The study of a Graphene Patch Antennas (GPA) equipped with gold-patched graphene MTS to serve as a superstrate arrangement is presented. Initially, proposed GPA design is simulated. Once the design process is completed in CST, the data collection is done. Then, the Convolutional Neural Network (CNN) model is trained using collected data from CST. As per the work, optimal tuning of antenna components is done that integrates components like Substrate length, Substrate width, Patch length, Patch width, Feed length, Width of feed, Substrate thickness, and Ground thickness. For this, a new Reverse Learning Initialization with Chimp Updated OOA (RLI-CHIOOA) algorithm is proposed in this work. The optimal selection of GPA components is done based on minimizing constraints like return loss, reflection coefficient and gain. Finally, the performance of the proposed work is validated over conventional models in terms of different performance metrics.