Dr. Petr Musilek received Ing. degree in Electrical Engineering (1991) and PhD degree in Technical Cybernetics (1995) from the Military Technical Academy in Brno, Czech Republic. In 1997, he was awarded a NATO Science Fellowship, tenured at the Intelligent Systems Research Laboratory, University of Saskatchewan, Canada. Since 1999, he has been with the University of Alberta, where he is presently a Professor and an Associate Chair (Research and Planning). He is a registered Professional Engineer in Alberta (APEGA), and a Senior Member of IEEE.
Dr. Musilek's energy-related research focuses on the use of ICT to support the design and operation of future electric power grids. He studies the integration of renewables and distributed energy resources (DER) in power systems, concentrating on energy management of grid-connected photovoltaic (PV) systems, battery energy storage systems (BESS), and electric vehicles. He also examines how weather impacts the energy production and consumption patterns, and the characteristics and integrity of the power delivery infrastructure (dynamic thermal rating, ice accretion). To deal with the complexity and uncertainty of modern distributed energy systems, he often employs high-performance computing and methods of computational intelligence, including machine learning, neural networks, fuzzy systems, evolutionary computing, and swarm systems. His current projects include:
Currently and in the past, my research has been supported by the following agencies CFI, CFREF, MITACS, NSERC, and by a number of industrial sponsors and research partners, including Alberta Electric System Operator (AESO), Altalink, ATCO Electric, EPCOR Distribution and Transmission Inc., NVIDIA, BC Transmission Corporation, BC Hydro, Bonneville Power Administration, EDF Energy, Hydro Quebec, NALCOR Energy, NB Power, TEPCO, Landmark group, and ACQBUILT.
The unique combination of research in intelligent systems, energy, and the environment, provides students in Dr. Musilek’s research group with rich opportunities to prepare for academic and industrial careers in these exciting and sought after fields.
Intelligent systems for automatic control and data analysis. The concepts of vagueness and uncertainty, approximate reasoning, fuzzy rule-based systems and fuzzy control. Strategies for learning and adaptation, supervised and reinforcement learning, self-organization and the selection of neural network architectures. Discussion of the principles of search and optimization, evolution and natural selection and genetic algorithms. Introduction to hybrid intelligence. Applications of intelligent systems for pattern recognition, classification, forecasting, decision support, and control. Credit may be obtained in only one of CMPE 449 or ECE 449.Fall Term 2020