Search Results for author: Patrick de Mars

Found 3 papers, 1 papers with code

Reinforcement Learning and Tree Search Methods for the Unit Commitment Problem

1 code implementation12 Dec 2022 Patrick de Mars

When generator outages are considered, guided tree search saves over 2\% in operating costs as compared with methods using conventional $N-x$ reserve criteria.

Decision Making reinforcement-learning +1

Reinforcement Learning and Mixed-Integer Programming for Power Plant Scheduling in Low Carbon Systems: Comparison and Hybridisation

no code implementations9 Dec 2022 Cormac O'Malley, Patrick de Mars, Luis Badesa, Goran Strbac

We find that deterministic and stochastic MIP consistently produce lower-cost UC schedules than RL, exhibiting better reliability and scalability with problem size.

Reinforcement Learning (RL) Scheduling

Cannot find the paper you are looking for? You can Submit a new open access paper.