 ELECO 2025 Invited Talks |
Kevin TOMSOVIC Clemson University The Holcombe Department of Electrical and Computer Engineering South Carolina, USA E-mail: ktomsov@clemson.edu Abstract – Conventional planning and operation studies for integrating new generation depends on labor-intensive time-domain simulations and extensive domain expertise, limiting their scalability and accessibility. For example, in the US, this has led to major backlogs for integrating utility-scale renewable resources into the grid. This talk will introduce our approach to performing analysis of proposed new power plants using a large language model (LLM) to assist the engineers. By harnessing the learning and data-processing strengths of a domain-specific LLM, this work aims to develop an LLM based framework that rapidly evaluates system security under various load conditions and fault scenarios. The LLM is trained on a rich body of power system data and literature, including domain knowledge from textbooks and research papers, simulation tools (e.g., ANDES and AMS), other documentation, and practical examples, to perform grid analyses. Validation is conducted against established simulation tools using standard test systems and real-world data. The outcome is a domain-specific, scalable LLM tool that enhances the grid planning studies, offering a complementary tool for engineers performing grid stability assessment as well as a useful tool for students. The talk will overview the design and show results of our research to date. |
 Professor Kevin TOMSOVIC Biography - Dr. Tomsovic received the B.S. degree in electrical engineering from Michigan Technological University, Houghton, in 1982 and the M.S. and Ph.D. degrees in electrical engineering from the University of Washington, Seattle, in 1984 and 1987, respectively. Currently, he is Executive Director of the Clemson University – Charleston Innovation Campus. Prior to joining Clemson University, he was a Chancellor’s Professor and the CTI Professor in the Department of Electrical Engineering and Computer Science (EECS) at University of Tennessee, Knoxville (UTK).  He was Director of the graduated NSF/DOE Engineering Research Center entitled CURENT from 2011 to 2024. He was Department Head of EECS at UTK from 2008-2013. He was on the faculty of Washington State University from 1992-2008. He held the Advanced Technology for Electrical Energy Chair at Kumamoto University, Kumamoto, Japan, from 1999 to 2000 and was an NSF program director in the ECS division from 2004 to 2006. Visiting University positions have included Boston University, Boston, MA; National Cheng Kung University, Tainan, Taiwan, R.O.C.; National Sun Yat-Sen University, Kaohsiung, Taiwan, R.O.C.; and the Royal Institute of Technology, Stockholm, Sweden. He is a member of the National Academy of Engineering and a Fellow of the IEEE.
His research focuses on modern computational methods that can address the complexities and uncertainties inherent in the future power grid with high levels of renewables and electrified transportation. Research Interests: Dr. Tomsovic’s areas of interest include intelligent systems and optimization methodologies applied to various power system problems, including distribution system design, electricity market analysis, equipment diagnostics and maintenance, operation of dispersed energy resources, production scheduling, and stabilization control. More details can be found at http://web.eecs.utk.edu/~ktomsovi/. |
