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 heterogenous 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
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
-
, , , , , 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
Datasets
Below you will find information about available datasets in the field of utilities.
- 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
- Batter 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 work “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. VBN. Quality_criteria_for_EPC_data(.pdf). 10.5278/7e93e42e-38fc-4d87-ad68-ff1a2d1091aa”
- 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).