In this area, we address broad range of questions on operational resilience of microgrids, power systems, and interlinked infrastructures such as water-energy microgrids. Active research topics include:
In this area, we address broad range of questions on how to identify differential equations of nonlinear systems from available data, optimize dynamical systems using learning algorithms and data-driven optimization techniques, and how to utilize data-driven models or direct control of dynamical systems with available data. Active research topics include:
Data-driven nonlinear model identification of distributed energy resources via statistical learning (read a paper via this link)
Data-driven control of nonlinear systems with statistical learning (read a paper via this link)
Deep learning- and Physics-informed optimization and energy management in smart grids (read a paper via this link)
In this area, we address broad range of questions on how to train machine learning algorithms to learn an optimal control problem of dynamical systems with available data. Active research topics include:
Deep learning-based model predictive control (this research is ongoing)
Deep learning-based energy management in microgrids (this research is ongoing)
In this area, we address broad range of questions on how to operate interdependent infrastructures including water and energy systems. We explore the energy management and control problems for water-energy microgrids using optimization and control theories. Active research topics include: