Dinesh Krishnamoorthy
Associate Professor, Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU)
-480.webp)
O.S. Bragstads plass 2D
Room D439
7034 Trondheim, Norway
Short bio
Dinesh Krishnamoorthy is an Associate Professor at the Department of Engineering Cybernetics, NTNU, where he leads the COLLAB research group. From 2022 to 2025 he was an Assistant Professor at the Department of Mechanical Engineering at TU Eindhoven, in the Control Systems Technology group, where he remains a Visiting Professor. From 2021 to 2022 he was a postdoctoral researcher at the Harvard John A. Paulson School of Engineering and Applied Sciences.
He received his PhD in Process Systems Engineering from NTNU, his MSc in Control Systems from Imperial College London, and his BEng in Mechatronics from the University of Nottingham. He also has more than four years of industrial research experience, as a Senior Researcher at the Statoil Research Centre in Norway (2012–2016) and as a part-time Senior Data Science Consultant for Novo Nordisk R&D (2021).
Selected honours and grants:
- FRIPRO Early Career Talent Grant, Research Council of Norway (2026)
- Member, Norwegian Academy of Young Researchers (2026)
- NTNU Outstanding Academic Fellows Programme (2026)
- IFAC Journal of Process Control Paper Prize, Theory category (2023–26)
- NWO VENI grant (2023) and EuroTech Future Award (2023)
- Dimitris N. Chorafas Foundation Award for best PhD thesis, one of 35 worldwide (2020)
- Excellence in Computer-Aided Process Engineering (CAPE) PhD Award, EFCE (2020)
- NTNU Faculty of Natural Sciences Best PhD Thesis Award (2021)
- IFAC Young Author Award
Research interests
My research lies at the intersection of optimization, control, and machine learning, with a focus on collaborative decision making in complex engineering systems: how many interacting subsystems or agents can coordinate their decisions toward a common goal, safely and in real time, using only limited information.
Distributed optimization & feedback-optimizing control
Decomposition-based algorithms and feedback control structures that steer large-scale interconnected systems to optimal operation directly from measurements.
Model predictive control
Distributed, mixed-integer, and learning-based MPC: learned controllers and value functions that keep MPC's guarantees.
Bayesian optimization for real-time decisions
Sample-efficient learning to optimize in real-time where constraint violations are not an option.