Search Results for author: Bert Claessens

Found 4 papers, 0 papers with code

Physics Informed Neural Networks for Control Oriented Thermal Modeling of Buildings

no code implementations23 Nov 2021 Gargya Gokhale, Bert Claessens, Chris Develder

To combine the interpretability of white/gray box physics models and the expressive power of neural networks, we propose a physics informed neural network approach for this modeling task.

Reinforcement Learning Applied to an Electric Water Heater: From Theory to Practice

no code implementations29 Nov 2015 Frederik Ruelens, Bert Claessens, Salman Quaiyum, Bart De Schutter, Robert Babuska, Ronnie Belmans

A wellknown batch reinforcement learning technique, fitted Q-iteration, is used to find a control policy, given this feature representation.

Decision Making

Experimental analysis of data-driven control for a building heating system

no code implementations13 Jul 2015 Giuseppe Tommaso Costanzo, Sandro Iacovella, Frederik Ruelens, T. Leurs, Bert Claessens

From the quantitative analysis it has been found that the control approach converges in approximately 20 days to obtain a control policy with a performance within 90% of the mathematical optimum.

Decision Making

Residential Demand Response Applications Using Batch Reinforcement Learning

no code implementations8 Apr 2015 Frederik Ruelens, Bert Claessens, Stijn Vandael, Bart De Schutter, Robert Babuska, Ronnie Belmans

We propose a model-free Monte-Carlo estimator method that uses a metric to construct artificial trajectories and we illustrate this method by finding the day-ahead schedule of a heat-pump thermostat.

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