Date of Award


Document Type


Degree Name

Master of Science (MS)


Electrical and Computer Engineering

Committee Chair/Advisor

Dr. Ganesh Kumar Venayagamoorthy

Committee Member

Dr. Rajendra Singh

Committee Member

Dr. Yingjie Lao


As modern electric power distribution systems (MEPDS) continue to grow in complexity, largely due to the ever-increasing penetration of Distributed Energy Resources (DERs), particularly solar photovoltaics (PVs) at the distribution level, there is a need to facilitate advanced operational and management tasks in the system driven by this complexity, especially in systems with high renewable penetration dependent on complex weather phenomena.

Digital twins (DTs), or virtual replicas of the system and its assets, enhanced with AI paradigms can add enormous value to tasks performed by regulators, distribution system operators and energy market analysts, thereby providing cognition to the system. DTs of MEPDS assets and the system can be utilized for real-time and faster-than-real-time operational and management task support, planning studies, scenario analysis, data analytics and other distribution system studies.

This study leverages DT and AI to enhance DER integration in an MEPDS as well as operational and management (O&M) tasks and distribution system studies based on a system with high PV penetration. DTs have been used to both estimate and predict the behavior of an existing 1 MW plant in Clemson University by developing asset digital twins of the physical system. Solar irradiance, temperature and wind-speed variations in the area have been modeled using physical weather stations located in and around the Clemson region to develop ten virtual weather stations. Finally, DTs of the system along with virtual and physical weather stations are used to both estimate and predict, in short time intervals, the real-time behavior of potential PV plant installations over the region. Ten virtual PV plants and three hybrid PV plants are studied, for enhanced cognition in the system. These physical, hybrid and virtual PV sources enable situational awareness and situational intelligence of real-time PV production in a distribution system.

Author ORCID Identifier




To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.