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 • 27 Oct 2023 • Varsha Behrunani, Philipp Heer, John Lygeros
As future energy systems become more decentralised due to the integration of renewable energy resources and storage technologies, several autonomous energy management and peer-to-peer trading mechanisms have been recently proposed for the operation of energy hub networks based on optimization and game theory.
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 • 4 Jul 2023 • Varsha Behrunani, Marta Zagorowska, Mathias Hudoba de Badyn, Francesco Ricca, Philipp Heer, John Lygeros
Mitigating the energy use in buildings, together with satisfaction of comfort requirements are the main objectives of efficient building control systems.
no code implementations • 27 Apr 2023 • Varsha Behrunani, Hanmin Cai, Philipp Heer, Roy S. Smith, John Lygeros
Joint operation of such hubs can improve energy efficiency and support the integration of renewable energy resource.
no code implementations • 24 Apr 2023 • Varsha Behrunani, Francesco Micheli, Jonas Mehr, Philipp Heer, John Lygeros
Historical data is used to build a demand prediction model based on Gaussian processes to generate a forecast of the future electricity and heat demands.
no code implementations • 9 Feb 2023 • Varsha Behrunani, Andrew Irvine, Giuseppe Belgioioso, Philipp Heer, John Lygeros, Florian Dörfler
Several autonomous energy management and peer-to-peer trading mechanisms for future energy markets have been recently proposed based on optimization and game theory.
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).
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.
no code implementations • 29 Oct 2021 • Felix Bünning, Benjamin Huber, Adrian Schalbetter, Ahmed Aboudonia, Mathias Hudoba de Badyn, Philipp Heer, Roy S. Smith, John Lygeros
However, we also see that the physics-informed ARMAX models have a lower computational burden, and a superior sample efficiency compared to the Machine Learning based models.
no code implementations • 25 Oct 2021 • Hanmin Cai, Philipp Heer
However, there remains a gap in comprehensive field insights into emission reduction, flexibility provision, and user impacts.
no code implementations • 25 Oct 2021 • Nami Hekmat, Hanmin Cai, Thierry Zufferey, Gabriela Hug, Philipp Heer
Real-time quantification of residential building energy flexibility is needed to enable a cost-efficient operation of active distribution grids.
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.
no code implementations • 26 Nov 2020 • Felix Bünning, Adrian Schalbetter, Ahmed Aboudonia, Mathias Hudoba de Badyn, Philipp Heer, John Lygeros
We assess the consequences of the additional constraints for the model accuracy and test the models in a real-life MPC experiment in an apartment in Switzerland.
no code implementations • 4 Nov 2020 • Fazel Khayatian, Andrew Bollinger, Philipp Heer
With the recent interest in installing building energy management systems, the availability of data enables calibration of building energy models.
no code implementations • 15 Sep 2020 • Felix Bünning, Joseph Warrington, Philipp Heer, Roy S. Smith, John Lygeros
By combining a control scheme based on Robust Model Predictive Control, with affine policies, and heating demand forecasting based on Artificial Neural Networks with online correction methods, we offer frequency regulation reserves and maintain user comfort with a system comprising a heat pump and buffer storage.