Rate My Professor Terrence Mak

Mak's research interests center on mathematical and combinatorial optimization, machine learning, and energy systems, including electric power transmission and natural gas pipeline systems. His primary focus involves developing novel methodologies that combine machine learning and optimization to tackle major climate change challenges in the energy sector, such as energy sustainability, net-zero emissions, climate-change resiliency, and disaster management. He is a Chief Investigator on projects like Grid Guru: Leveraging AI-Driven Grid Optimisation and a collaboration with RedGrid to enhance software modeling and planning algorithms. Key publications include 'Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods' (2020, Proceedings of the AAAI Conference on Artificial Intelligence, 338 citations), 'Lagrangian Duality for Constrained Deep Learning' (2020), 'Differential Privacy for Power Grid Obfuscation' (2019, IEEE Transactions on Smart Grid, 95 citations), 'Compact Optimization Learning for AC Optimal Power Flow' (2024, IEEE Transactions on Power Systems), 'Learning Regionally Decentralized AC Optimal Power Flows with ADMM' (2023, IEEE Transactions on Smart Grid), and 'Mitigation of Overvoltage in PV-Rich Distribution System using Decentralised Control of EV Charging' (2025, IEEE Transactions on Transportation Electrification). Mak has contributed to ARPA-E U.S. Department of Energy initiatives including the Grid Optimization Competition (2019-2023), collaborated with national laboratories such as Los Alamos, NREL, and PNNL, and industry partners like RTE France, Midcontinent ISO, and Origin Energy. He serves on senior program committees for conferences including IJCAI (2021-2022), AAMAS (2023), and ECAI (2023), and accepts PhD students for topics at the intersection of deep learning and nonlinear optimization for smart grids.