Julian Oelhaf

Lehrstuhl für Informatik 5 (Mustererkennung)

Research associates

Address

Martensstraße 3
91058 Erlangen

Contact

julian.oelhaf@fau.de
+49 9131 85-27775
lme.tf.fau.de/

Julian Oelhaf

I am a doctoral researcher at the Pattern Recognition Lab, FAU Erlangen-Nürnberg. My research lies at the intersection of machine learning and power systems, with a focus on intelligent power system protection. In particular, I study fault detection, classification, line identification, and localization in future power grids.

The growing integration of renewable energy, power-electronic converters, and distributed generation creates increasingly variable grid conditions. These developments challenge conventional protection schemes designed for more predictable system behavior. My work investigates how machine learning can enable fast, robust, and interpretable protection decisions under these conditions.

I aim to bring academic research closer to real-world grid operation through reproducible benchmarks, scalable data pipelines, and simulation-based validation. I am also interested in collaborations with utilities, grid operators, technology providers, and industrial partners working toward reliable and resilient energy systems.

AI Grid Protection – Coordinated Power System Protection using Machine Learning

  • 2024 – present | Doctoral Researcher, Pattern Recognition Lab, FAU
  • 2021 – 2024 | M.Sc. in Computer Science, FAU
  • 2017 – 2020 | B.Sc. in Aerospace Computer Science, JMU Würzburg

2024

  • Netzschutz-KI: Coordinated grid protection based on machine learning methods

    (Third Party Funds Single)

    Project leader: , ,
    Term: July 1, 2024 - June 30, 2027
    Acronym: Netzschutz-KI
    Funding source: DFG-Einzelförderung / Sachbeihilfe (EIN-SBH)

2026

Journal Articles

Conference Contributions

Unpublished Publications

2025

Journal Articles

Conference Contributions

Open Positions

Title Type Student Period
Machine Learning on Real-World Power Grid Oscillograms Project

Current Theses & Projects

Title Type Student Period Status
Cross-Topology Generalization of Spatiotemporal Graph Neural Networks for Power System Protection MA thesis Jithin Baby Sep 2026 – Feb 2027 running
Federated Learning for Local Fault Analysis in Power Systems BA thesis Lukas Bayer Sep 2026 – Feb 2027 running
Parameter-Conditioned Deep Learning for Fault Localization in Power Grids MA thesis Muhammad Zain Sep 2026 – Mar 2027 running
Universal and Relay-Generalizable Machine Learning for Protection in Power Grids Project Nithin Pradeep Nadayil Kizhakkethil Apr 2026 – Aug 2026 running
Machine Learning for Cyber-Physical Event Detection in Smart Grids Project Alexander Denner Jun 2026 – Sep 2026 running
Parameter Efficient Finetuning of Universal Time Series Transformers for Energy Forecasting MA thesis Aliullah Aliullah Mar 2026 – Aug 2026 running

Completed Theses & Projects

Title Type Student Period Status
Surrogate Modeling Based on Machine Learning Approaches for Hospitals as Microgrids MA thesis Mihir Nandaniya Jan 2026 – Jun 2026 finished
Known Operator Learning for Fault Localization in Electric Power Grids MA thesis Sagar Sikdar Feb 2026 – Aug 2026 finished
Reinforcement Learning Based Coordinated Protection Using Conventional Relay Models Project Pushpak Mitra Jan 2026 – Jun 2026 finished
Classification of the State of Electrical Contacts of Circuit Breakers with Explainable Artificial Intelligence BA thesis Thomas Zimmermann Dec 2025 – Apr 2026 finished
Evaluating Time-Frequency Representations for Intelligent Fault Analysis in Power System Protection Project Prodipto Haldar Oct 2025 – Mar 2026 finished
Multi-Task Learning for Integrated Fault Analysis in Power System Protection Project Rahul Bhagwandas Motwani Oct 2025 – Mar 2026 finished
Reinforcement Learning for Adaptive Protection in Power Grids MA thesis Omar Sehata Sep 2025 – Mar 2026 finished
Offline Reinforcement Learning on a Real-World Power Grid Control Problem Project Alexander Luce Mar 2026 – Jun 2026 finished
Reinforcement Learning for Centralized Fault Coordination in Power Systems Project Jithin Baby May 2025 – Nov 2025 finished
Transformer-Based Forecasting Model for Fault Detection in Power System Protection Project Sagar Sikdar Apr 2025 – Oct 2025 finished
Advanced Machine Learning-Based High Demand Forecasting of Household Energy Consumption for Enhancing Grid Operations MA thesis Souhardya Chattopadhyay Aug 2025 – Feb 2026 finished
Deep Learning-Based Fault Detection and Classification in Power System Protection: A Comparative Study MA thesis Tamoghna Ghosh Mar 2025 – Sep 2025 finished
Wind Power Forecasting through Probabilistic Machine Learning Models MA thesis Mohammad Hasan Khan Nov 2024 – May 2025 finished