1 code implementation • 23 Nov 2023 • Loris Di Natale, Muhammad Zakwan, Philipp Heer, Giancarlo Ferrari Trecate, Colin N. Jones
This manuscript details the SIMBa toolbox (System Identification Methods leveraging Backpropagation), which uses well-established Machine Learning tools for discrete-time linear multi-step-ahead state-space System Identification (SI).
1 code implementation • 6 Nov 2023 • Loris Di Natale, Muhammad Zakwan, Bratislav Svetozarevic, Philipp Heer, Giancarlo Ferrari-Trecate, Colin N. Jones
Machine Learning (ML) and linear System Identification (SI) have been historically developed independently.
no code implementations • 1 Oct 2023 • Wenjie Xu, Bratislav Svetozarevic, Loris Di Natale, Philipp Heer, Colin N Jones
We study the problem of tuning the parameters of a room temperature controller to minimize its energy consumption, subject to the constraint that the daily cumulative thermal discomfort of the occupants is below a given threshold.
no code implementations • 23 Dec 2022 • Loris Di Natale, Bratislav Svetozarevic, Philipp Heer, Colin Neil Jones
While physically sound, classical gray-box models are often cumbersome to identify and scale, and their accuracy might be hindered by their limited expressiveness.
no code implementations • 30 Nov 2022 • Loris Di Natale, Bratislav Svetozarevic, Philipp Heer, Colin N. Jones
Model-free Reinforcement Learning (RL) generally suffers from poor sample complexity, mostly due to the need to exhaustively explore the state-action space to find well-performing policies.
no code implementations • 11 Nov 2022 • Muhammad Zakwan, Loris Di Natale, Bratislav Svetozarevic, Philipp Heer, Colin N. Jones, Giancarlo Ferrari Trecate
Since IPHS models are consistent with the first and second principles of thermodynamics by design, so are the proposed Physically Consistent NODEs (PC-NODEs).
no code implementations • 31 May 2022 • Loris Di Natale, Yingzhao Lian, Emilio T. Maddalena, Jicheng Shi, Colin N. Jones
This manuscript offers the perspective of experimentalists on a number of modern data-driven techniques: model predictive control relying on Gaussian processes, adaptive data-driven control based on behavioral theory, and deep reinforcement learning.
1 code implementation • 10 Mar 2022 • Loris Di Natale, Bratislav Svetozarevic, Philipp Heer, Colin N. Jones
Replacing poorly performing existing controllers with smarter solutions will decrease the energy intensity of the building sector.
1 code implementation • 6 Dec 2021 • Loris Di Natale, Bratislav Svetozarevic, Philipp Heer, Colin N. Jones
To counter this known generalization issue, physics-informed NNs have recently been introduced, where researchers introduce prior knowledge in the structure of NNs to ground them in known underlying physical laws and avoid classical NN generalization issues.
1 code implementation • CISBAT 2021 • Loris Di Natale, Bratislav Svetozarevic, Philipp Heer, Colin Neil Jones
Deep Reinforcement Learning (DRL) recently emerged as a possibility to control complex systems without the need to model them.