Introducing statistical and machine learning-based methods of enhancing the resiliency and security of electrical-based critical infrastructure

Since its introduction into society in the late 1800’s, electricity has become a critical component in how society has functioned. High-voltage electricity provides power for appliances that have become integral to daily living, such as lights, refrigeration, and Heating, Ventilation, And Cooling (HVAC). Low-voltage electricity is used to process and transmit information on and between computers. This information may pertain to medical, financial, and defense-related activities. Over the past hundred years, significant research has been performed to improve electrical-based technology’s capability, scale, resiliency, and security. This study focuses solely on resiliency and security, both of which require efficient data collection, storage, and processing. In the case of the resiliency of high-voltage electrical transmission, the continuous, 24-hour collection of transmission line activity generates data that exceeds the ability to store for long-term forensics. For the secure transmission of information, the information must be (i) hard to recover by an adversary and (ii) trusted by the recipient. This dissertation presents research aimed at (i) improving the reliability of High-voltage electrical transmission by statistically compressing data at the edge by up to 99.96% while still maintaining actionable information to enable real-time Incipient Fault Prediction (IFP), (ii) reducing an adversary’s ability to intercept information by introducing AI-based, session-based cryptographic scheme generation, and (iii) improving information’s trust by identifying the source of wireless transmission at the physical layer by enabling cross-collection Specific Emitter Identification (SEI) at up to 99.51% blind collection accuracy across eight commercial emitters.

Grantor dc:publisher

University of Tennessee at Chattanooga

Year dc:date.available

2026

Author dc:creator

• Tyler, Joshua

Contributors dc:contributor

• Reising, Donald R.
• Loveless, Thomas Daniel; Sartipi, Mina; Fadul, Mohamed
• College of Engineering and Computer Science

• Artificial intelligence
• Data encryption (Computer science)
• Electric power distribution
• Information warfare
• Machine learning

Licence

• http://rightsstatements.org/vocab/InC/1.0/

Language dc:language

English, eng

Repository record dc:identifier

https://scholar.utc.edu/theses/1024

OAI identifier oai:identifier

oai:scholar.utc.edu:theses-2209