Integration of DL on Multi-Carrier Non-Orthogonal Multiple Access System with Simultaneous Wireless Information and Power Transfer

Chaturvedi A.; Bhardwaj A.; Singh D.; Pant B.; Gonzales J.L.A.; Firos A. · Proceedings of the 2022 11th International Conference on System Modeling and Advancement in Research Trends, SMART 2022 (2022) · DOI: 10.1109/smart55829.2022.10046773

Resumen

Simultaneous Multi-Carrier (MC) NOMA&Wireless Information (SWIPT) are exciting ideas for coming net within the 5th generation and beyond because of their capability for allowing bandwidth and power effective system designs. Using the pattern-division-multiple-access (PDMA) approach, this study investigates the concurrent downlink scalability issue for a SWIPT-enabled MCNOMA system incorporating time swapping receivers. We put a lot of effort into reducing the systems overall transmit power while still providing each user with the level of service they expect in terms of gathered power and data rate. The corresponding optimization problem is a challenging quasi mixed integer computing problem. We present an effective deep learning (DL) based method as opposed to the traditional repetitive searching-based techniques for finding an approximation of the ideal answer. We particularly use a deep belief network (DBN), a common kind of DL model. The created technique's thorough technique is divided into three parts: data generation, testing, and execution. The simulated Results show that the suggested DBN-based strategy works. might produce results in terms of power usage that are similar to those of the thorough search technique. The findings also show that MCNOMA with PDMA outperforms MCNOMA with the other methods in terms of power consumption in systems that support SWIPT.

Instituciones: Pontificia Universidad Católica del Perú