This achievement is not only a personal milestone for David Fellner, but also underlines the success of the SIC! program in promoting cutting-edge research. SIC! was launched in collaboration with industry partners and research institutions and is now in its second round. It builds on the success of the first generation, which has produced eight dissertations and over fifty publications since 2018.
This academic achievement adds significance to the efforts of the DeMaDs project, a project David Fellner significantly contributed to. Its goal is to reshape the landscape of power grid monitoring.
Background and challenges
The integration of renewable energy sources has changed the traditional energy landscape and led to an increased complexity of grid operation and monitoring. One of the main problems faced by distribution system operators (DSOs) is the increase in voltage band violations due to the difficulty of monitoring the correct operation of grid-connected devices, especially inverters at the low-voltage level.
The monitoring of grid-connected devices is essential to ensure the reliability and proper functioning of the grid. However, the irregular updating of grid data and legal restrictions, such as obtaining customer consent to use smart meter data, are obstacles to effective monitoring. In addition, the cost-intensive expansion of communication infrastructures makes it difficult to process large volumes of local data centrally.
The DeMaDs project
The DeMaDs project was part of a comprehensive dissertation and aimed to develop a solution to these challenges by introducing a centralized data-driven approach. The primary goal was to create monitoring capabilities capable of detecting and distinguishing various misconfigurations, including incorrectly parameterized photovoltaic inverters, e-vehicle charging stations or improperly controlled loads.
In contrast to the current state of the art, the DeMaDs project has innovatively developed a complete framework for monitoring grid-connected devices. This framework integrates data mining, processing and validation of results and offers a new and efficient approach to tackle the complexity associated with grid management.
David Fellner's most important achievements
Data-driven anomaly detection: the project successfully developed a data-driven method for detecting abnormal readings from substation transformers. This ground-breaking approach fills a crucial gap in the detection of anomalies at the medium voltage level of substations by using operational data for higher accuracy.
Root cause analysis: DeMaDs provides a method to link abnormal behavior to the underlying cause by classifying detected anomalies into predefined types of misconfigurations. These valuable insights are crucial for developing a monitoring solution that goes beyond mere detection and provides a deeper understanding of the network's performance.
Extraction of information: The project developed an approach for extracting information about the low-voltage distribution network using centralized data. This is crucial as anomalies at the low-voltage level are difficult to detect without information extraction. The resolution of the aggregated power profiles enables the identification of factors contributing to anomalies.
Comprehensive assessment: DeMaDs conducted a thorough assessment of the data required for a potential monitoring solution, taking into account data characteristics, quality, provenance and monitoring performance. This ensures the feasibility of the monitoring solution and builds confidence in its functionality within the existing data infrastructure.
In the midst of these groundbreaking achievements, David Fellner, the driving force behind the DeMaDs project, successfully defended his PhD on February 24, 2024. His dedication and expertise have been instrumental in making the project a success and an important contribution to monitoring the electricity grid.
Future impact
The achievements of the DeMaDs project and David Fellner's recent academic success pave the way for more efficient and reliable energy grid management. The data-driven approach not only improves anomaly detection, but also provides key insights for proactive grid maintenance. As the energy landscape evolves, innovations such as the DeMaDs project will play a crucial role in ensuring the seamless integration of renewable energy sources into our power distribution systems.
Partnerships at the core
The NextGeneration SIC! thrives on collaboration. As a cooperative doctoral program at TU Wien, it works closely with partners from various research institutions, including the Austrian Institute of Technology (AIT) and the Montanuniversität Leoben (MUL). Cooperation with industry is also of crucial importance: large companies such as A1, EVN, evon and Fundermax contribute to the success of the college. This collaborative approach ensures that the research carried out is both scientifically sound and relevant to practice.
The NextGeneration SIC! paves the way for future advances and the success of researchers like David Fellners serves as inspiration for the next wave of innovators ready to tackle the complex challenges of our ever-evolving industrial landscape in the context of climate change.
David Fellner is currently Head of the Renewable Energy program and Senior Lecturer and Researcher at FH Technikum Wien. We wish him continued success on his professional and scientific path.
David Fellners PhD thesis is publically available via TU Wien reposiTUm, opens an external URL in a new window:
Fellner, D. (2024). Data Driven Detection of Misconfigurations in Power Distribution Systems, opens an external URL in a new window [Dissertation, Technische Universität Wien]. reposiTUm.
The following papers were written as part of his dissertation:
Published Publications:
- Fellner, D., Strasser, T., Kastner, W. (2023). Misconfiguration Detection of Inverter-based Units in Power Distribution Grids using Machine Learning to be published in Arghandeh, R., & Zhou, Y. (Eds.). (2023). Big data application in power systems, 2nd edition. Elsevier.
- Fellner, D., Strasser, T., Kastner, W. (2023). Data-driven misconfiguration detection in power systems with transformer profile disaggregation, submitted to IEEE ACCESS
- Fellner, D., Strasser, T., Kastner, W. (2023). An operational data-driven malfunction detection framework for enhanced power distribution system monitoring – the demads approach. In Proceedings of the CIRED 2023
- Fellner, D., Strasser, T., Kastner, W. (2023). The DeMaDs Open Source Modeling Framework for Power System Malfunction Detection. In Proceedings of the 2023 OSMSES, Aachen, Germany, 2023, pp.1-6
- Fellner, D., Strasser, T., Kastner, W., Behnam, F., & Abdulhadi, I. F. (2022). Data Driven Transformer Level Misconfiguration Detection in Power Distribution Grids. in Proceedings of 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (S. 1832-1839)
- Fellner, D., Strasser, T., & Kastner, W. (2022). Applying Deep Learning-based concepts for the detection of device misconfigurations in power systems. Sustainable Energy, Grids and Networks, 32
- Fellner, D., Strasser, T., & Kastner, W. (2021). Detection of Misconfigurations in Power Distribution Grids using Deep Learning. in Proceedings of the 2021 Int. Conference on Smart Energy Systems and Technologies (SEST)
- Herbst, D., Schürhuber, R., Henein, S., Zehetbauer, P., Fellner, D., Einfalt, A., Schmautzer, E., & Fickert, L. (2021). Entwicklung und Evaluierung eines Algorithmus zur automatisierten Rekonfiguration von Niederspannungsnetzen. e&i elektrotechnik und informationstechnik, 525-537.
- Fellner, D. (2020). Data Driven Detection of Malfunctions in Power Systems. Energy Informatics 2020, 22-24.
- Fellner, D., Brunner, H., Strasser, T., & Kastner, W. (2020). Towards Data-Driven Malfunctioning Detection in Public and Industrial Power Grids. in Proceedings of the 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)"
"Research Partnerships – Industrial PhD Program” in DeMaDs (FFG No. 879017)