Philipp Heer

Philipp Heer
Philipp Heer
PI
It is truly exciting to develop solutions towards a sustainable energy system for society by the means of collaboration and applied research in control.

Philipp Heer is the deputy head of the Urban Energy Systems Lab (UESL) at Empa - an Institute of the ETH Domain and is responsible for the energy and digitalization related research at the Empa demonstrators NEST, move and ehub. He received a BSc from HSLU T&A (2010) and a MSc from ETH Zurich (2013) both in Electrical, Electronics and Communications Engineering and a MAS from ETH Zurich (2018) in Management, Technology, and Economics. His research focusses on developing operational solutions based on data-driven approaches to foster a sustainable energy system.

Scientific Publications

Published
Stable Linear Subspace Identification: A Machine Learning Approach
ArXiv
Published
Computationally Efficient Reinforcement Learning: Targeted Exploration leveraging simple Rules
ArXiv
Published
Physically Consistent Neural ODEs for Learning Multi-Physics Systems
Proceedings of IFAC World congress 2023
to Appear
Physically Consistent Neural Networks for building thermal modeling: theory and analysis
Applied Energy
Vol 325
Published
Uncertainty-Aware Energy Flexibility Quantification of a Residential Building
2023 ISGT Europe
Pages 1-6
Published
Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control
IEEE 17th International Conference on Control & Automation (ICCA)
Pages 698-703
Published
Data-driven control of room temperature and bidirectional EV charging using deep reinforcement learning: Simulations and experiments
Applied Energy
Vol 307 Pages 118127
Published
Deep Reinforcement Learning for Room Temperature Control: A Black-box Pipeline from Data to Policies
CISBAT 2021 special issue of IOP's JOURNAL OF PHYSICS Conference Series
Vol 2042
The Potential of Vehicle-to-Grid to Support the Energy Transition: A Case Study on Switzerland
MDPI Energies
Vol 14 No 16

Research projects

Title
Principal Investigators

Probabilistic prosumer side flexibilities for multi use-case applications

Summary

The electric energy demand of buildings is increasing due to the electrification of the transportation and heating systems. While this puts an additional strain on the power grid, EVs and heat pumps (among others) are flexible loads that can be leveraged to keep the balance between generation and load. Coincidently, smart meters and edge computing resources (i.e. building automation systems) are deployed providing the means to access this flexibility. Hence, in this project, we will leverage building data to develop detailed models for the quantification and usage of flexibility at the building level for different time scales.

Probabilistic prosumer side flexibilities for multi use-case applications

The electric energy demand of buildings is increasing due to the electrification of the transportation and heating systems. While this puts an additional strain on the power grid, EVs and heat pumps (among others) are flexible loads that can be leveraged to keep the balance between generation and load. Coincidently, smart meters and edge computing resources (i.e. building automation systems) are deployed providing the means to access this flexibility. Hence, in this project, we will leverage building data to develop detailed models for the quantification and usage of flexibility at the building level for different time scales.

190
c0bfb8d4-028d-43f0-ac62-762f1c3631a8

Deep Reinforcement Learning for Building Control: Physics-inspired Methods

Summary

Buildings consume 30% and 40% of the end-use energy in Europe and worldwide respectively, but the increasing amount of sensors installed in new or retrofitted buildings gives rise to new data-driven control opportunities. Most controllers in existing buildings are however still rule-based, due to the required engineering to develop more advanced methods, such as Model Predictive Control (MPC). On the other hand, Reinforcement Learning (RL) has received increasing attention in the past years as a decision making paradigm that bypasses the need for models. Instead, an agent learns to take optimal decisions solely by interacting with the environment and getting rewarded/penalized for it.

We conjecture that incorporating prior physics-based knowledge in the model architectures or learning procedures will be a stepping stone towards generally applicable - i.e. data-efficient and reliable - DRL approaches. In this work, we will thus explore various solutions to introduce prior knowledge in models and DRL agents, design algorithms to apply them to buildings, and deploy the resulting controllers on case studies to assess their advantages in practice, primarily focusing on the building energy systems installed at the Empa NEST demonstrator.

Deep Reinforcement Learning for Building Control: Physics-inspired Methods

Buildings consume 30% and 40% of the end-use energy in Europe and worldwide respectively, but the increasing amount of sensors installed in new or retrofitted buildings gives rise to new data-driven control opportunities. Most controllers in existing buildings are however still rule-based, due to the required engineering to develop more advanced methods, such as Model Predictive Control (MPC). On the other hand, Reinforcement Learning (RL) has received increasing attention in the past years as a decision making paradigm that bypasses the need for models. Instead, an agent learns to take optimal decisions solely by interacting with the environment and getting rewarded/penalized for it.

We conjecture that incorporating prior physics-based knowledge in the model architectures or learning procedures will be a stepping stone towards generally applicable - i.e. data-efficient and reliable - DRL approaches. In this work, we will thus explore various solutions to introduce prior knowledge in models and DRL agents, design algorithms to apply them to buildings, and deploy the resulting controllers on case studies to assess their advantages in practice, primarily focusing on the building energy systems installed at the Empa NEST demonstrator.

189
077ed802-beee-4804-94de-2b0e3109b69d

Research projects as Researcher

Title
Principal Investigators

Decentralized control of multi-energy systems

Summary

Electrical, thermal and chemical processes follow individual demand and supply patterns under distinct time scales, from sub-second (electrical) to weekly (thermal) and seasonal (chemical) applications. In these applications, digitalization enables a coordination of the related technologies. So, next to sector specific technological limitations, the systemic coupling of energy carriers needs to take into account  the coupling of different time scales as well as different production and consumption patterns. As the technological landscape is getting more decentral in terms of energy production, also more stakeholders are involved in the energetic supply chain. These actors can benefit if they share information on their capabilities and intended production and consumption. Moreover, information sharing and local decision making could potentially reduce the need for extending large-scale infrastructure, such as transmission grids or international imports of energy. The project investigates the use of distributed decision making and control methods to address the large scale nature of the problem, as well as data driven methods to deal with the uncertainty inherent in the problem. Validation of the methodological approach is foreseen on the NEST building at Empa.

Decentralized control of multi-energy systems

Electrical, thermal and chemical processes follow individual demand and supply patterns under distinct time scales, from sub-second (electrical) to weekly (thermal) and seasonal (chemical) applications. In these applications, digitalization enables a coordination of the related technologies. So, next to sector specific technological limitations, the systemic coupling of energy carriers needs to take into account  the coupling of different time scales as well as different production and consumption patterns. As the technological landscape is getting more decentral in terms of energy production, also more stakeholders are involved in the energetic supply chain. These actors can benefit if they share information on their capabilities and intended production and consumption. Moreover, information sharing and local decision making could potentially reduce the need for extending large-scale infrastructure, such as transmission grids or international imports of energy. The project investigates the use of distributed decision making and control methods to address the large scale nature of the problem, as well as data driven methods to deal with the uncertainty inherent in the problem. Validation of the methodological approach is foreseen on the NEST building at Empa.

113
34ab7ee3-eae2-4be6-a009-595eb7b858b4

News & Insights

24-10-2023
Sisslerfeld
On October 24, 2023, the founding meeting of the "Reallabor Sisslerfeld" took place in Münchwilen. The "Verein" (association) will concentrate on creating a living lab for energy and mobility topics. Among those present at the ceremony were Dieter Egli, Cantonal Government Councillor of Aargau and the President of ETH Zurich, Joël Mesot, as well as other high-ranking representatives from politics, administration, research and industry.