Daniel Bayer

Phone	(0931) 31-89632
E-Mail	daniel.bayer@uni-wuerzburg.de
Room	01.019 (Building M4)
Address	Lehrstuhl für Informatik XI Am Hubland 97074 Würzburg Germany

Google Scholar | Researchgate | LinkedIn | ORCID

Research Interests

Daniel Bayer works as a research assistant at the Chair of Computer Science (Modelling and Simulation). He first studied mathematics with a Bachelor of Science degree, then computer science at the Friedrich-Alexander-Universität Erlangen-Nürnberg.
His work focuses on the research project of DigiSWM. Here, one of the central goals is to combine extensive energy data with AI methods to simulate and evaluate new energy services.

His research interests include digital twins and data-driven simulations of local energy systems, including the building sector, to ensure long-term sustainable and climate-neutral energy supply through the optimal dimensioning and control of heating and energy supply systems. He also deals with the topics of multi-agent reinforcement learning and sustainable computing.

Research projects

Recent Publications

2024[ to top ]

Data-driven heat pump retrofit analysis in residential buildings: Carbon emission reductions and economic viability. Bayer, Daniel R.; Pruckner, Marco. In Applied Energy, 373, p. 123823. Elsevier BV, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ DOI ]
Heat pumps replacing existing gas furnaces, the predominant heating system in Europe, are crucial for achieving global CO2 emission reduction targets. Previous studies have simulated this reduction potential for a few buildings, revealing substantial variations in results. Moreover, additional CO2 emission reductions are proven to be possible with photovoltaic installations and battery energy storage systems. However, as these come with high investment costs, the question remains whether these are economically viable. Moreover, as the building stock shows a high degree of diversity and the heat demand is dependent on the annual weather conditions, the CO2 emission reduction and the cost-effectiveness of incorporating photovoltaics or battery systems should be analyzed for all buildings in a city over multiple years. In this paper, we address these questions by utilizing a digital twin of a German city encompassing all residential buildings, capturing the diversity of the building stock. Our findings indicate that retrofitting heat pumps, only considering the heating system, reduces average annual CO2 emissions by 18.6% to 38.9% across different years. The variance in emission reduction, up to 1.6 percentage points, is not year-dependent. The maximum CO2 reduction on the building level is achieved by combining heat pumps with photovoltaic and battery systems for most buildings, averaging a 31.2% to 43.6% reduction even in a Central European climate with low winter photovoltaic generation. Economically, a heat pump retrofit with photovoltaic installation emerges as the most beneficial setting for most buildings in the studied city, effectively balancing cost and emission reduction.

@article{2024_Bayer_AppliedEnergy, abstract = {Heat pumps replacing existing gas furnaces, the predominant heating system in Europe, are crucial for achieving global CO2 emission reduction targets. Previous studies have simulated this reduction potential for a few buildings, revealing substantial variations in results. Moreover, additional CO2 emission reductions are proven to be possible with photovoltaic installations and battery energy storage systems. However, as these come with high investment costs, the question remains whether these are economically viable. Moreover, as the building stock shows a high degree of diversity and the heat demand is dependent on the annual weather conditions, the CO2 emission reduction and the cost-effectiveness of incorporating photovoltaics or battery systems should be analyzed for all buildings in a city over multiple years. In this paper, we address these questions by utilizing a digital twin of a German city encompassing all residential buildings, capturing the diversity of the building stock. Our findings indicate that retrofitting heat pumps, only considering the heating system, reduces average annual CO2 emissions by 18.6% to 38.9% across different years. The variance in emission reduction, up to 1.6 percentage points, is not year-dependent. The maximum CO2 reduction on the building level is achieved by combining heat pumps with photovoltaic and battery systems for most buildings, averaging a 31.2% to 43.6% reduction even in a Central European climate with low winter photovoltaic generation. Economically, a heat pump retrofit with photovoltaic installation emerges as the most beneficial setting for most buildings in the studied city, effectively balancing cost and emission reduction.}, author = {Bayer, Daniel R. and Pruckner, Marco}, journal = {Applied Energy}, keywords = {pruckner}, month = 11, pages = 123823, publisher = {Elsevier BV}, title = {Data-driven heat pump retrofit analysis in residential buildings: Carbon emission reductions and economic viability}, volume = 373, year = 2024 }
Electricity Demand Forecasting in Future Grid States: A Digital Twin-Based Simulation Study. Bayer, Daniel R.; Haag, Felix; Pruckner, Marco; Hopf, Konstantin. In 2024 9th International Conference on Smart and Sustainable Technologies (SpliTech), pp. 1–6. IEEE, 2024.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ DOI ]
Short-term forecasting of residential electricity demand is an important task for utilities. Yet, many small and medium-sized utilities still use simple forecasting approaches such as Synthesized Load Profiles (SLPs), which treat residential households similarly and neither account for renewable energy installations nor novel large consumers (e.g., heat pumps, electric vehicles). The effectiveness of such “one-fits-all” approaches in future grid states—where decentral generation and sector coupling increases—are questionable. Our study challenges these forecasting practices and investigates whether Machine Learning (ML) approaches are suited to predict electricity demand in today's and in future grid states. We use real smart meter data from 3,511 households in Germany over 34 months. We extrapolate this data with future grid states (i.e., increased decentral generation and storage) based on a digital twin of a local energy system. Our results show that Long Short-Term Memory approaches outperform SLPs as well as simple benchmark estimators with up to 68.5% lower Root Mean Square Error for a day-ahead forecast, especially in future grid states. Nevertheless, all prediction approaches perform worse in future grid states. Our findings therefore reinforce the need (a) for utilities and grid operators to employ ML approaches instead of traditional demand prediction methods in future grid states and (b) to prepare current ML methods for future grid states.

@inproceedings{10612563, abstract = {Short-term forecasting of residential electricity demand is an important task for utilities. Yet, many small and medium-sized utilities still use simple forecasting approaches such as Synthesized Load Profiles (SLPs), which treat residential households similarly and neither account for renewable energy installations nor novel large consumers (e.g., heat pumps, electric vehicles). The effectiveness of such “one-fits-all” approaches in future grid states—where decentral generation and sector coupling increases—are questionable. Our study challenges these forecasting practices and investigates whether Machine Learning (ML) approaches are suited to predict electricity demand in today's and in future grid states. We use real smart meter data from 3,511 households in Germany over 34 months. We extrapolate this data with future grid states (i.e., increased decentral generation and storage) based on a digital twin of a local energy system. Our results show that Long Short-Term Memory approaches outperform SLPs as well as simple benchmark estimators with up to 68.5% lower Root Mean Square Error for a day-ahead forecast, especially in future grid states. Nevertheless, all prediction approaches perform worse in future grid states. Our findings therefore reinforce the need (a) for utilities and grid operators to employ ML approaches instead of traditional demand prediction methods in future grid states and (b) to prepare current ML methods for future grid states.}, author = {Bayer, Daniel R. and Haag, Felix and Pruckner, Marco and Hopf, Konstantin}, booktitle = {2024 9th International Conference on Smart and Sustainable Technologies (SpliTech)}, keywords = {pruckner}, month = {06}, pages = {1-6}, publisher = {IEEE}, title = {Electricity Demand Forecasting in Future Grid States: A Digital Twin-Based Simulation Study}, year = 2024 }

2023[ to top ]

Modeling of Annual and Daily Electricity Demand of Retrofitted Heat Pumps based on Gas Smart Meter Data. Bayer, Daniel R.; Pruckner, Marco. In Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, of BuildSys ’23. ACM, 2023.
- [ BibTeX ]
- [ URL ]
- [ DOI ]
@inproceedings{bayer2023modeling, author = {Bayer, Daniel R. and Pruckner, Marco}, booktitle = {Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation}, keywords = {pruckner}, month = 11, publisher = {ACM}, series = {BuildSys ’23}, title = {Modeling of Annual and Daily Electricity Demand of Retrofitted Heat Pumps based on Gas Smart Meter Data}, year = 2023 }
A digital twin of a local energy system based on real smart meter data. Bayer, Daniel; Pruckner, Marco. In Energy Informatics, 6(1). Springer Science and Business Media {LLC}, 2023.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ DOI ]
The steadily increasing usage of smart meters generates a valuable amount of high-resolution data about the individual energy consumption and production of local energy systems. Private households install more and more photovoltaic systems, battery storage and big consumers like heat pumps. Thus, our vision is to augment these collected smart meter time series of a complete system (e.g., a city, town or complex institutions like airports) with simulatively added previously named components. We, therefore, propose a novel digital twin of such an energy system based solely on a complete set of smart meter data including additional building data. Based on the additional geospatial data, the twin is intended to represent the addition of the abovementioned components as realistically as possible. Outputs of the twin can be used as a decision support for either system operators where to strengthen the system or for individual households where and how to install photovoltaic systems and batteries. Meanwhile, the first local energy system operators had such smart meter data of almost all residential consumers for several years. We acquire those of an exemplary operator and discuss a case study presenting some features of our digital twin and highlighting the value of the combination of smart meter and geospatial data.

@article{2023_Bayer_DT_LocalEnergySystem, abstract = {The steadily increasing usage of smart meters generates a valuable amount of high-resolution data about the individual energy consumption and production of local energy systems. Private households install more and more photovoltaic systems, battery storage and big consumers like heat pumps. Thus, our vision is to augment these collected smart meter time series of a complete system (e.g., a city, town or complex institutions like airports) with simulatively added previously named components. We, therefore, propose a novel digital twin of such an energy system based solely on a complete set of smart meter data including additional building data. Based on the additional geospatial data, the twin is intended to represent the addition of the abovementioned components as realistically as possible. Outputs of the twin can be used as a decision support for either system operators where to strengthen the system or for individual households where and how to install photovoltaic systems and batteries. Meanwhile, the first local energy system operators had such smart meter data of almost all residential consumers for several years. We acquire those of an exemplary operator and discuss a case study presenting some features of our digital twin and highlighting the value of the combination of smart meter and geospatial data.}, author = {Bayer, Daniel and Pruckner, Marco}, journal = {Energy Informatics}, keywords = {pruckner}, month = {03}, number = 1, publisher = {Springer Science and Business Media {LLC}}, title = {A digital twin of a local energy system based on real smart meter data}, volume = 6, year = 2023 }

2022[ to top ]

Enhancing the Performance of Multi-Agent Reinforcement Learning for Controlling HVAC Systems. Bayer, Daniel; Pruckner, Marco. In 2022 IEEE Conference on Technologies for Sustainability (SusTech), pp. 187–194. 2022.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ DOI ]
Systems for heating, ventilation and air-conditioning (HVAC) of buildings are traditionally controlled by a rule-based approach. In order to reduce the energy consumption and the environmental impact of HVAC systems more advanced control methods such as reinforcement learning are promising. Reinforcement learning (RL) strategies offer a good alternative, as user feedback can be integrated more easily and presence can also be incorporated. Moreover, multi-agent RL approaches scale well and can be generalized. In this paper, we propose a multi-agent RL framework based on existing work that learns reducing on one hand energy consumption by optimizing HVAC control and on the other hand user feedback by occupants about uncomfortable room temperatures. Second, we show how to reduce training time required for proper RL-agent-training by using parameter sharing between the multiple agents and apply different pretraining techniques. Results show that our framework is capable of reducing the energy by around 6% when controlling a complete building or 8% for a single room zone. The occupants complaints are acceptable or even better compared to a rule-based baseline. Additionally, our performance analysis show that the training time can be drastically reduced by using parameter sharing.

@inproceedings{9794179, abstract = {Systems for heating, ventilation and air-conditioning (HVAC) of buildings are traditionally controlled by a rule-based approach. In order to reduce the energy consumption and the environmental impact of HVAC systems more advanced control methods such as reinforcement learning are promising. Reinforcement learning (RL) strategies offer a good alternative, as user feedback can be integrated more easily and presence can also be incorporated. Moreover, multi-agent RL approaches scale well and can be generalized. In this paper, we propose a multi-agent RL framework based on existing work that learns reducing on one hand energy consumption by optimizing HVAC control and on the other hand user feedback by occupants about uncomfortable room temperatures. Second, we show how to reduce training time required for proper RL-agent-training by using parameter sharing between the multiple agents and apply different pretraining techniques. Results show that our framework is capable of reducing the energy by around 6% when controlling a complete building or 8% for a single room zone. The occupants complaints are acceptable or even better compared to a rule-based baseline. Additionally, our performance analysis show that the training time can be drastically reduced by using parameter sharing.}, author = {Bayer, Daniel and Pruckner, Marco}, booktitle = {2022 IEEE Conference on Technologies for Sustainability (SusTech)}, keywords = {pruckner}, month = {04}, pages = {187-194}, title = {Enhancing the Performance of Multi-Agent Reinforcement Learning for Controlling HVAC Systems}, year = 2022 }

Research Interests

Research projects

Recent Publications

Hinweis zum Datenschutz

Hinweis zum Datenschutz

Bildnachweise