Digital Signal Processing and Machine Learning Applied to Power Line Communications
Date
2021-08
Authors
Thapa, Kushal
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Power Line Communications (PLC) is a technology that uses power lines to transport communication data alongside the electric power signals. Due to the ubiquitous nature of pre-existing power grid infrastructure, PLC has a huge networking potential, especially in the implementation of smart grid technologies. However, the electrical architecture and function of distribution grid systems, which is specifically designed to carry power signals, poses a major hindrance to communication signals. This hindrance typically takes the form of poor signal propagation. Traditional signal processing measures may be neither sufficiently adaptable nor optimally effective in recovering communication signals at the receiver end. To overcome this challenge, this research investigates the use of machine learning techniques as a supplement to the traditional digital signal processing techniques. We focus on testing and comparing various supervised machine learning and deep learning algorithms for the purpose of signal demodulation and bit classification in ultra-low-frequency, baseband PLC systems operating in the electrical distribution grid.
Description
Keywords
Power line communications, Ultra-low frequency power line communications, PLC, ULF-PLC, Machine learning, ML, Smart grid
Citation
Thapa, K. (2021). <i>Digital signal processing and machine learning applied to power line communications</i> (Unpublished thesis). Texas State University, San Marcos, Texas.