Research
Research Interests:
My research is in the intersection of dynamic modeling, control, and data-science with application domains including microgrids, power grids and buildings, water systems, and naval power systems.
Current Research:
1- Machine Learning for Smart Grid Optimization
I am interested in exploring data-driven methods for solving numerical optimization problems such as economic dispatch and optimal power flow in smart grids and microgrids. See selected articles in below.
X. Fang and J. Khazaei, "A Two-Stage Deep Learning Approach for Solving Microgrid Economic Dispatch," in IEEE Systems Journal, vol. 17, no. 4, pp. 6237-6247, Dec. 2023
J. Khazaei and F. Moazeni, "Neural Networks-Based Detection of Line Overflow Cyberattacks on AC State-Estimation of Smart Grids," in IEEE Systems Journal, vol. 17, no. 2, pp. 2399-2410, June 2023, doi: 10.1109/JSYST.2022.3201725.
Ge, X., & Khazaei, J. (2024). Physics-informed Convolutional Neural Network for Microgrid Economic Dispatch. arXiv preprint arXiv:2404.18362.
2- Data-Driven Modeling for Energy Systems
I explore data-driven modeling of distributed energy resources and dynamical systems in electricity infrastructure using statistical learning, machine learning, and emerging model-free approaches. Selected publications are listed in below.
Hosseinipour, A., & Khazaei, J. (2023). Sparse Identification for Data-Driven Dynamics and Impedance Modeling of Power Converters in DC Microgrids. IEEE Journal of Emerging and Selected Topics in Industrial Electronics.
J. Khazaei and F. Moazeni, "Model Identification of Distributed Energy Resources Using Sparse Regression and Koopman Theory," 2023 IEEE PES GTD International Conference and Exposition (GTD), Istanbul, Turkiye, 2023, pp. 33-38, doi: 10.1109/GTD49768.2023.00033.
Khazaei, J., & Hosseinipour, A. (2022). Advances in Data‐Driven Modeling and Control of Naval Power Systems. Transportation Electrification: Breakthroughs in Electrified Vehicles, Aircraft, Rolling Stock, and Watercraft, 453-473.
3- Data-Driven Control in Dynamical Systems
In this research thrust, I explore various methods to control dynamical systems without an explicit knowledge of their dynamics. A combination of data-driven model identification techniques such as Sparse Regression, Koopman Operator, or Machine learning is utilized for a model-free control design. See selected publications in this area in below.
Khazaei, J., & Hosseinipour, A. (2023). Data-Driven Feedback Linearization Control of Distributed Energy Resources using Sparse Regression. IEEE Transactions on Smart Grid.
Putri, S. A., Moazeni, F., & Khazaei, J. (2024). Data-driven predictive control strategies of water distribution systems using sparse regression. Journal of Water Process Engineering, 59, 104885.
Khazaei, J., Liu, W., & Moazeni, F. (2023, June). Data-driven sparse model identification of inverter-based resources for control in smart grids. In 2023 11th International Conference on Smart Grid (icSmartGrid) (pp. 1-6). IEEE.
4- Optimization, Control, and Security for Grid Interdependent Infrastructures
In this research area, I explore novel techniques for resource allocation and cybersecurity of resources in interdependent infrastructures such as water-energy, water-energy-building, or water-energy-transportation systems. We look for novel optimization techniques and machine learning approaches for real-time operation of interdependent infrastructures.
Putri, S. A., Moazeni, F., & Khazaei, J. (2023). Predictive control of interlinked water-energy microgrids. Applied Energy, 347, 121455.
Moazeni, F., & Khazaei, J. (2020). Optimal operation of water-energy microgrids; a mixed integer linear programming formulation. Journal of Cleaner Production, 275, 122776.
Moazeni, F., & Khazaei, J. (2021). Interactive nonlinear multiobjective optimal design of water distribution systems using Pareto navigator technique. Sustainable Cities and Society, 73, 103110.
5- Power Electronics and Hardware-in-the-loop Testing in Cyber-Physical Power Systems
In this research area, I focus on real-time and hardware in the loop (HIL) experimentation of power electronics converters with various control designs for grid-forming and grid-following mode of operation. Our laboratory has the capability for real-time simulations, hardware-in-the-loop tests of DERs with up to 10kW capacity, and power electronics-based control design.
Diller, J., Idowu, P., & Khazaei, J. (2020, February). Load-Leveling Trainer for Demand Side Management on a 45kW Cyber-Physical Microgrid. In 2020 IEEE Texas Power and Energy Conference (TPEC) (pp. 1-6). IEEE.
Diller, J., Trussell, B., Khazaei, J., & Idowu, P. (2020, February). Hardware Development of a Sinusoidal PWM on a Three-Phase 3.5 kW SiC Converter. In 2020 IEEE Texas Power and Energy Conference (TPEC) (pp. 1-6). IEEE.