A Machine Learning Based Energy-Efficient Non-Orthogonal Multiple Access Scheme

Rabia Khan, Dushanta Nalin Kumara Dzhayakodi Jayakody Arachshiladzh, Vishal Sharma, Vinay Kumar, Kuljeet Kaur, Zheng Chang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Applicability of Artificial Intelligent (AI) and NonOrthogonal Multiple Access (NOMA) have drawn remarkableattraction towards the implementation of 5th Generation (5G)wireless communication systems. 5G demands significant improvements in terms of data rate, throughput, reliability, Qualityof Service (QoS), fairness, Symbol Error Rate (SER), Outage,reliability and latency as compared to the current standards.The aforementioned parameters have a critical impact whenapplied to the Internet of Thing (IoT). Considering the demandof high power and energy, we have optimized Energy-Efficiency(EE) and Radio Frequency Energy Harvesting (RFEH) usingMachine Learning based Genetic Algorithm (MLGA). For thesystem integration, we proposed to Built-in Energy EfficientModulation based NOMA (BEEM-NOMA). BEEM NOMA isan energy efficient system that has the capability to prevent thewaste of energy. Combination of BEEM-NOMA with MLGAfurther enhances the performance of the system, as proved withthe simulation results in this paper.
Original languageEnglish
Title of host publication14th International Forum on Strategic Technology (IFOST-2019), October 14-17, 2019, Tomsk, Russia:[proceedings].—Tomsk, 2019.
Pages330-335
Number of pages6
Publication statusPublished - 2019

Fingerprint

Dive into the research topics of 'A Machine Learning Based Energy-Efficient Non-Orthogonal Multiple Access Scheme'. Together they form a unique fingerprint.

Cite this