Research

My research focuses on machine learning, deep learning, data analytics, and decision-making methods with applications to smart grid and power systems. I am particularly interested in:

• Reinforcement learning for energy management, storage scheduling, and capacity planning (e.g., PV-battery systems, microgrid storage expansion)
• Probabilistic and stochastic methods for distribution network equivalence, static security analysis, and uncertainty quantification
• Physics-informed neural networks and their applications in power system analysis
• Data-driven optimization for grids with high renewable penetration

I work on deep reinforcement learning-based capacity scheduling, bi-level adaptive storage expansion, adaptive static equivalences for active distribution networks, and probabilistic equivalence with correlated uncertain injections. For more details, see my publications.