Application of Adaptive Hybrid Deep Learning for Power System State Estimation

Presented by: Qun Zhou, Assistant Professior, University of Central Florida

Click Here to Stream

Deep learning is powerful in data-driven applications, such as computer vision and natural language processing. Power system state estimation is data-driven in nature as the amount of measurement data is rapidly increasing with emerging sensing technology. This research explores the possibility of applying deep learning for power system state estimation. The proposed adaptive hybrid deep learning model, which incorporates the physical power flow mode, is both data driven and first principle based. It is trained in real time and intended for online state estimation. 

Conventional state estimation is considered as single-snapshot, which estimates system variables by only using the measurement data at the moment. In fact, power system states are intrinsically correlated in time, but the true dynamics are very challenging to model. In this research, deep learning is employed to learn this dynamics and temporal correlations are explored among historical measurements. Two deep learning networks, feedforward neural net and long short-term memory net, are investigated.  Results are presented in IEEE 14-bus and118-bus systems in terms of accuracy and robustness. The applicability and potential challenges are discussed. 

INTENDED AUDIENCE: People who work in academia and industry, and possibly government and regulatory bodies



Mark SiiraDr. Qun Zhou is an Assistant Professor of Electrical Engineering at University of Central Florida. She received her B.S. from Huazhong University of Science and Technology, and Ph.D. from Iowa State University, both in Electrical Engineering. Dr. Zhou worked at GE grid solutions as a power system engineer and developed electricity market software for major U.S. transmission operators. Her research is focused on applying machine learning and probability theory to enhance power system operation and planning, as well as power economics and markets


For any questions, please contact Phyllis Caputo at

To view previous webinars on-demand, visit the IEEE Smart Grid Resource Center