Data Processing for Utility Infrastructure
Our group aims to tackle the challenges faced in the utility/industrial/real estate infrastructure through statistical, Machine Learning and Deep Learning approaches with an emphasis to mitigate climate change. To this end, we focus on digitizing and integrating data from heterogeneous sources, embedding knowledges and enable techniques that increase operational efficiency and reduce carbon emissions. We deal with time-series data (e.g., consumption data from smart meters), GIS data (e.g., network topology, geolocations of network components), SCADA data (network performance, e.g., pumps). Our current research revolves around database modelling, development of digital twin for utility networks (e.g., as a knowledge graph) as well as ML and DL algorithms for different applications such as load predictions, time-series clustering, anomaly detection/localization and data exploration.
Projects
Start: November 1, 2023
End: October 31, 2026
Description:
The United Nations' goals for sustainable development have made improving quality of life and access to clean drinking water a political priority. However, in recent decades, the water cycle in Bavaria has also been significantly affected by climate change. Two important aspects of daily drinking water supply and distribution are the assurance of water quality and the increase in usage efficiency. To enhance the resilience and capacity of the water supply in general, numerical simulation, data integration, and artificial intelligence (AI) are necessary. In this project, we aim to develop an AI-refined temperature-hydraulic model using heterogeneous data sources from a Bavarian water supply network. Hybrid AI methods are employed to model the complex relationship between water and soil temperature. The resulting model will serve as the basis for various real applications such as leak detection, anomaly recognition, and monitoring of drinking water quality, with the overarching goal of increasing the efficiency and quality of the water supply while simultaneously contributing to the containment of the impact of climate change on drinking water supply
Start: September 1, 2021
End: August 31, 2024
Description:
In the UtilityTwin research project, an intelligent digital twin for any energy or water supply network is to be researched and developed on the basis of adaptive high-resolution sensor data (down to the sub-second range) and machine learning techniques. Overall, the technology concepts BigData and AI are to be combined in an innovative way in this research project in order to make positive contributions to the implementation of the energy transition and to counteract climate change.
Participating Scientists
Changhun Kim, M. Sc.
- Phone number: +49 9131 85-27872
- Email: changhun.kim@fau.de
- Website: https://lme.tf.fau.de/person/chkim/
Julian Oelhaf, M. Sc.
- Phone number: +49 9131 85-27872
- Email: julian.oelhaf@fau.de
- Website: https://lme.tf.fau.de/person/juoelhaf
Dr.-Ing. Siming Bayer, Dr. -Ing
- Mobile phone: +4917622520695
- Email: siming.bayer@fau.de
- Website: https://lme.tf.fau.de/person/sbayer/
Colloquium time table
Publications
- , , , , , , , A Systematic Evaluation of Machine Learning Methods for Fault Detection and Line Identification in Electrical Power Grids. In: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
-
, , , , Advancing Heat Demand Forecasting with Attention Mechanisms: Opportunities and Challenges. In: NeurIPS 2024
The Thirty-Eighth Annual Conference on Neural Information Processing Systems, 2024
Access via: https://www.climatechange.ai/papers/neurips2024/26
- , , , , , , , Creating a labeled district heating data set: From anomaly detection towards fault detection. In: , 2024
- , , , , Unveiling Consumer Behavior in District Heating Network: A Contrastive Learning Approach to Clustering. In: SESAAU2024 – Smart Energy Systems Conference, 2024
-
, , , , , Heat Demand Forecasting with Multi-Resolutional Representation of Heterogeneous Temporal Ensemble. In: NeurIPS 2022 Workshop Tackling Climate Change with Machine Learning, 2022
Access via: https://www.climatechange.ai/papers/neurips2022/46
-
, , , Prediction of Household-level Heat-Consumption using PSO enhanced SVR Model. In: Tackling Climate Change with Machine Learning: workshop at NeurIPS 2021, 2021
Access via: https://www.climatechange.ai/events/neurips2021.html#accepted-works
-
, , , , , , , , Implications of Experiment Set-Ups for Residential Water End-Use Classification. In: Water, , 2021, DOI: 10.3390/w13020236
Access via: https://www.mdpi.com/2073-4441/13/2/236
Open Positions
Below you will find information about available datasets in the field of utilities.
Water
- TU Berlin – Smart Water Networks (Github)
In their work “Urban Water Consumption at Multiple Spatial and Temporal Scales. A Review of Existing Datasets”, authored by Di Mauro, A., Cominola, A., Castelletti, A., & Di Nardo, A. in 2021 (paper), various water datasets are described. Along with water, their work entails datasets on district heating and electricity – GitRepo.
- Battle of Water Demand Forecasting
The dataset was made available as part of a competition during the 3rd International Joint Conference on Water Distribution Systems Analysis & Computing and Control for the Water Industry (WDSA/CCWI). The data describes urban water demand in a set of 10 real District Metered Areas (DMAs).
- Aalborg University
Datasets across water and heat at hourly resolution are made available for the Danish city of Aalborg – Dataset. The work is documented in their publication: “Schaffer, M. (Ophavsperson), Veit, M. (Bidrager), Marszal-Pomianowska, A. (Datamanager), Frandsen, M. (Bidrager), Pomianowski, M. Z. (Bidrager), Dichmann, E. (Bidrager), Sørensen, C. G. (Bidrager), Kragh, J. (Bidrager) (27 Nov. 2023).
Dataset of smart heat and water meter data with accompanying building characteristics – Dataset - Department of Environmental Technology – Universität Innsbruck
The research group provides datasets and tools for urban water management research. Their anonymized water distribution datasets offer real-world hydraulic models for analysis. virtRome is a large-scale benchmark case study for network optimization. They also support infrastructure modeling and urban drainage simulations – (link).
- Stillwell Research Group – UIUC
The Stillwell Research Group at UIUC provides datasets on water and energy sustainability. Their residential water use and university housing shower data help analyze consumption patterns. Electricity usage in multi-family housing is linked with socioeconomic factors, while non-potable water reuse data supports water conservation research. These datasets aid in understanding and optimizing water-energy systems – (link).
Heat
- Aalborg University – Energy and Buildings Research Group
The Energy and Buildings Research Group provides datasets on energy efficiency, human activity, and sustainability in the built environment. Their Smart Heat and Water Meter Data covers five years of consumption patterns in Danish homes, aiding in resource optimization. Additional datasets include indoor environmental quality and occupancy data for improving energy-efficient living conditions and desiccant evaporative cooling system data for sustainable cooling solutions. These datasets support interdisciplinary research on water and energy sustainability – Dataset, All datasets.
- IEA – District Heating and Cooling
The IEA District Heating and Cooling initiative provides datasets on simulated faults in district heating systems. Their Simulated Faults dataset includes 28 days of operational data, supporting AI-driven fault detection and optimization in thermal energy networks. In their work “Generation and evaluation of a synthetic dataset to improve fault detection in district heating and cooling systems” (2023), the authors analyze these datasets to enhance system efficiency and reliability through machine learning techniques – Dataset.
- Harbin, China – District Heating System Leakage Dataset
This simulated dataset models leakage scenarios in district heating systems (DHS) in Harbin, China, supporting research on fault detection and system optimization. The dataset enables the development of AI-driven strategies for detecting and diagnosing leaks in large-scale heating networks. In their work “Simulation and Detection of Leakages in District Heating Networks” (2020), the authors utilize this dataset to enhance leakage monitoring and improve the resilience of DHS infrastructure. Dataset-I, Publication.
- Switzerland – Bundesamt für Energie (BFE)
The Swiss Federal Office of Energy (Bundesamt für Energie) provides a dataset containing high-level information on district heating infrastructure across Swiss cities. This dataset includes details on energy sources, municipal utilities (Stadtwerke), the number of connections, and supply networks, aiding research on urban energy distribution and sustainability. Dataset, Dataset.
- Munich – OpenData FFE
The OpenData FFE platform provides the Load Profiles of the Residential Sector – Dynamis Reference Scenario (Germany) dataset, offering detailed insights into household energy consumption patterns. This dataset, available in JSON format, supports research on energy demand modeling, smart grid optimization, and sector coupling strategies. Dataset.
- Stadtwerke Flensburg GmbH – Zentrum für nachhaltige Energiesysteme
The Zentrum für nachhaltige Energiesysteme provides hourly district heating supply data, including return temperatures, from the Stadtwerke Flensburg GmbH network. The dataset covers the years 2014 to 2016 and 2017 to 2019. Dataset, Dataset.
- Sønderborg Varme A/S – Zentrum für nachhaltige Energiesysteme
The Zentrum für nachhaltige Energiesysteme provides a dataset containing 15-minute sampled district heating supply data, including feed and return flow temperatures, from Sønderborg Varme A/S in Denmark. Covering the years 2016 to 2019. Dataset.
- University of Oulu – Energy and Environmental Engineering
The Energy and Environmental Engineering research group at the University of Oulu focuses on sustainable and carbon-neutral energy systems. They have developed a dataset titled “Dataset of future district heating energy demand in a Finnish municipality”, which provides hourly resolution data for a heating season in Jyväskylä, Finland. Dataset.
- Halmstad University – District Heating and Cooling Research Group
The District Heating and Cooling Research Group at Halmstad University focuses on enhancing the efficiency and sustainability of district heating systems. They provide hourly district heating data for two large districts in Sweden. Dataset, Dataset.
- RWI Essen – Research Data Center Ruhr (FDZ)
The Research Data Center Ruhr at RWI Essen focuses on energy efficiency and the impact of energy policy on residential heating. They provide the German Heating and Housing Panel (GHHP) dataset, which offers comprehensive data on heating behaviors and housing characteristics in Germany. This resource supports research on energy consumption patterns and policy evaluation. Dataset.
- TU Delft – Faculty of Civil Engineering and Geosciences
The Faculty of Civil Engineering and Geosciences at TU Delft has developed a multi-energy system model to simulate the integration of High-Temperature Aquifer Thermal Energy Storage (HT-ATES). Their dataset accompanies the publication “Towards sustainable heat supply with decentralized multi-energy systems by integration of subsurface seasonal heat storage,” providing valuable insights into sustainable heat supply solutions. Dataset.
Power
- RTE France Transmission System Operator
This dataset includes detailed voltage and current waveform signals captured from high-voltage lines in the French electricity transmission grid, specifically during fault conditions. Dataset
- Grid Energy Storage Lab
This platform provides datasets focused on grid energy storage systems, including performance metrics, operational efficiency, and system behavior under various conditions. Dataset
- JRC EMHIRES
This dataset offers high-resolution time series data on wind power generation across Europe, enabling detailed analysis of wind energy integration and its impact on the power grid. Dataset
- RTE France Data Analysis and Data
This resource provides comprehensive datasets on electricity consumption, generation, and grid operations in France, supporting research and analysis of energy trends and grid performance. Dataset
- TenneT
This dataset offers transparency data on electricity markets, including real-time generation, consumption, and grid balancing information, with a focus on the German and Dutch markets. Dataset
- Green Grid Compass
This dataset focuses on the environmental impact of electricity grids, providing metrics on carbon emissions, sustainability, and the integration of renewable energy sources. Dataset
- ENTSO-E
This platform provides extensive pan-European electricity market data, including generation, consumption, and transmission statistics, supporting cross-border energy analysis and research. Dataset, Dataset
- TransnetBW
This dataset offers detailed market data on electricity transmission, including grid load, balancing power, and other key operational metrics for the German grid. Dataset, Dataset
- REN Data Hub
This platform provides datasets on electricity transmission and market operations in Portugal, offering insights into grid performance and energy market dynamics. Dataset
- Open Power System Data
This resource offers open datasets on European power systems, including generation, consumption, and grid balancing data, facilitating research on energy transition and grid management. Dataset
- Aalborg University – Faculty of Engineering and Science
This dataset focuses on uncertainty in model-based fault detection for power systems, providing valuable insights for improving grid reliability and fault analysis. Dataset
- Amprion
This dataset provides detailed information on grid operations, including load flows, generation data, and cross-border electricity exchanges, supporting analysis of grid stability and market dynamics. Dataset
- SMARD
This platform offers comprehensive and transparent data on the German electricity market, including detailed information on electricity generation, consumption, and market trends, supporting energy market analysis. Dataset
- National Grid ESO (Electricity System Operator)
This dataset provides insights into the electricity transmission network in Great Britain, including data on electricity demand, generation, and grid balancing, with a focus on renewable energy integration. Dataset
- Energinet
This dataset, provided by Denmark’s transmission system operator, covers electricity generation, consumption, and grid operations, with a strong emphasis on renewable energy and cross-border electricity trading. Dataset, Dataset