ML for Power Systems
Machine learning applications in power system operation and planning
Research Summary
Research on machine learning for power systems explores data-driven methods for forecasting, anomaly detection, and decision support in grid operation and planning. This includes applications in load forecasting, renewable generation prediction, and optimization under uncertainty.
Publications
Partially-Supervised Neural Network Model For Quadratic Multiparametric Programming
Submitted to Computers and Operations Research (Second Revision), 2025.
A Neural Network Framework for Discovering Closed-Form Solutions to Quadratic Programs with Linear Constraints
Submitted to INFORMS Journal on Computing, 2025.
Semi-Supervised Neural Network Model For Quadratic Multiparametric Programming
arXiv preprint, 2025.
Constraint-Guided Deep Neural Network for Solving Optimal Power Flow
Electric Power Systems Research, 2022.
Robust training for AC-OPF (student abstract)
Proceedings of the AAAI Conference on Artificial Intelligence, 2023.
Solver-Free Data Generation for Training Neural Networks with Applications in Power Flow Analysis
2025 IEEE Electrical Power and Energy Conference (EPEC), 2025.