Year

2020

Degree Name

Doctor of Philosophy

Department

School of Electrical, Computer and Telecommunications Engineering

Abstract

Visible light communications (VLC) employ visible light for communication within the frequency spectrum from 430 THz to 790 THz. The ultra-wide bandwidth resolves the spectrum exhaustion in radio frequency communications. Light-fidelity (LiFi) takes VLC further to achieve high speed, bi-directional and fully networked wireless communications. Light-emitting diode (LED) is the major light source employed by LiFi as LED is energy efficient for illumination, and at the same time can achieve high speed data transmission thanks to the LED fast switching capability. Now, LED communications, one of the major application scenarios of LiFi, have attracted huge attention and research interests. A variety of advantages are offered including the unregulated wide bandwidth, energy efficiency, safety, etc., which makes LED communications a promising supplement to the fifth generation (5G) communications. LED is the major source of nonlinearity in LED communications and LED also exhibits significant memory effect in the case of high data rate, which degrade the system performance severely. Hence, the nonlinear distortion and memory effect need to be handled properly. Polynomial based methods have been proposed to address the issue in the literature. However, the conventional polynomial based techniques suffer from numerical instability easily in determining the coefficients of the polynomials, resulting in significantly compromised performance.

The objective of this thesis is to develop efficient and effective methods to mitigate the nonlinearity and memory effects in LED communications. In particular, the extreme learning machine (ELM) is considered for its fast learning and simplicity for implementation. ELM randomly assigns its hidden nodes (i.e., input weights and biases) and keeps them fixed, and only its output weights need to be determined, which is far more efficient than the conventional machine learning methods where back-propagation is required. Although, the work in the thesis focuses on LED communications, it can be easily extended to wireless radio communications to handle the hardware impediments, such as the nonlinearity of power amplifiers.

FoR codes (2008)

0801 ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING, 1005 COMMUNICATIONS TECHNOLOGIES

Share

COinS
 

Unless otherwise indicated, the views expressed in this thesis are those of the author and do not necessarily represent the views of the University of Wollongong.