Digital Signal Processing and Machine Learning Applied to Power Line Communications

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.

Name thesis:degree_name

Master of Science

Level thesis:degree_level

Masters

Discipline thesis:degree_discipline

Engineering

Grantor

Texas State University

Year dc:date.issued

2021

Author dc:creator

• Thapa, Kushal

Advisor dc:contributor.advisor

• McClellan, Stan

Committee members dc:contributor.committeemember

• Valles, Damian
• Aslan, Semih
• Carvallo, Andres

• power line communications
• ultra-low frequency power line communications
• PLC
• ULF-PLC
• machine learning
• ML
• smart grid

Language dc:language.iso

en

Handle dc:identifier.uri

https://hdl.handle.net/10877/14044

OAI identifier oai:identifier

oai:digital.library.txst.edu:10877/14044