Michael Bidollahkhani
| michael.bkhani@uni-goettingen.de | |
| Address | RZGö, Burckhardtweg 4, Georg-August Universität Göttingen, room 2.102 |
Biography
Michael Bidollahkhani is a computer engineer and AI researcher at the University of Göttingen, working under the supervision of Prof. Dr. Julian Martin Kunkel. His research focuses on artificial intelligence for reliable computing and intelligent infrastructure, including predictive maintenance, observability-aware anomaly detection, HPC and AI systems, and autonomous data-driven decision support. His work includes research on GPU failure analysis, compute-continuum reliability, agentic AI, and scalable machine intelligence. He received Young Scientist recognitions from the YSF of Iran in 2017 and 2023, selected as young doctoral researcher member of AI Grid and an Artificial Intelligence Specialist of the EU GUILD, and has contributed to international research, reviewing, and scientific program activities.
ORCID: 0000-0001-8122-4441
Google Scholar: https://scholar.google.com/citations?user=_rLezLYAAAAJ
Research Interests
- Artificial Intelligence
- Intelligent Infrastructure Systems
- AI for Infrastructure Reliability
- Predictive Maintenance
- Observability and Anomaly Detection
- High-Performance Computing
- Emergent Intelligence
Projects
Advisory roles
- 2026, Program Committee Member, The 40th Annual AAAI Conference on Artificial Intelligence - AI Alignment Track (AAAI-26-AIA)
- 2025, Elected Member, Parliament of International Students (PaIS), University of Göttingen
- 2025, Session Chair, The International Conferences on Digital Technology Driven Engineering 2025 (hosted by Jordan University of Science and Technology)
- 2024, Track Chair, The Eighteenth International Conference on Advanced Engineering Computing and Applications in Sciences; AISys, ICSEA, CENTRIC tracks
Journal review duties
- 2026, The 11th International Conference on Smart Cities & Applications (SCA2026)
- 2026, The International Conference on Electrical and Computer Engineering Researches (ICECER 2026)
- 2026, Frontiers in Computational Neuroscience
- 2025, FinTech and Sustainable Innovation (FSI)
- 2023, The American Journal of Artificial Intelligence (AJAI)
- 2020, IEEE Signal Processing Society
Teaching
Autumn Term 2027
Summer Term 2027
Autumn Term 2026
Summer Term 2026
Autumn Term 2025
Summer Term 2025
Autumn Term 2024
Open Thesis Topics
Monitoring and Controlling Irregular Behavior in Agentic AI Systems with Access to Digital and Physical ResourcesApply
In this thesis, researchers works on a new class of risks emerging from agentic AI systems that are able to perform actions, use tools, access resources, execute software, control devices, or make operational decisions. As AI systems move from passive recommendation toward automated decision-making and action execution, it becomes important to monitor whether an agent behaves within its allowed boundaries. The main objective is to design a lightweight monitoring and control framework that can detect irregular, unauthorized, or suspicious behavior in AI agents. Such behavior may include executing unexpected commands, accessing restricted files, modifying system settings, using tools outside the assigned task, consuming abnormal resources, or making decisions that conflict with predefined rules and human intentions. The project may focus on software agents operating on desktop or operating-system-level environments, AI assistants executing automated tasks, business-process agents managing resources, or simulated cyber-physical agents interacting with actuators. The student will define allowed and disallowed behavior patterns, collect or simulate agent activity logs, and develop a monitoring mechanism that can detect deviations from expected behavior. A Master thesis may focus on implementing and evaluating a prototype supervisory system that monitors agent actions and detects rule violations. A PhD-level thesis may extend the work by developing a more general framework for runtime agent governance, combining rule-based monitoring, machine learning, anomaly detection, policy checking, formal constraints, and human-in-the-loop approval mechanisms. A possible motivating example is a business or resource-management scenario in which an autonomous assistant supervises financial or operational decisions and prevents risky or unauthorized actions by another actor. This illustrates the broader need for trusted third-party AI supervisors that monitor agents and enforce operational boundaries.
Environmental Sustainability Labeling for AI Services Based on Energy, Runtime, and Resource UsageApply
This thesis focuses on designing a transparent labeling system for evaluating the environmental impact of AI services. The main idea is to measure how much computational effort, runtime, memory, CPU, GPU, and energy an AI service requires, and then translate these measurements into a simple and understandable label. The labeling concept can be inspired by energy labels used for household appliances, such as A, B, C, D, and E. However, the student has freedom to define the exact scoring method, evaluation metrics, and visualization style. The AI services may include classification models, generative AI models, anomaly detection tools, scheduling systems, or other selected AI applications. A Bachelor thesis can focus on implementing a prototype and evaluating a small number of AI models. A Master thesis can extend the work by designing a more formal scoring model, comparing multiple infrastructures, or including sustainability indicators such as estimated carbon impact.
Meta Machine Intelligence for Adaptive Error Detection in High-Performance Computing SystemsApply
This thesis investigates how multiple AI models can be used together for detecting errors, failures, and abnormal behavior in high-performance computing systems. Instead of relying on one fixed detection model, the system should analyze the current situation and select the most suitable model based on system context. The context may include workload behavior, node status, resource usage, error patterns, log messages, or historical system behavior. The student can explore different strategies such as model selection, ensemble learning, rule-based routing, machine learning-based routing, or LLM-assisted log interpretation. A Bachelor thesis may compare several anomaly detection models on HPC or server logs. A Master thesis may design an adaptive Meta Machine Intelligence layer that selects the best model depending on the current system condition.
Lightweight Edge AI for Detecting Irregular Behavior in Device and Sensor LogsApply
This thesis aims to develop a lightweight anomaly detection system for device logs, sensor data, or small-scale monitoring environments. The focus is on AI methods that can operate under limited computational resources, such as embedded systems, Raspberry Pi devices, IoT nodes, or edge computing environments. The system should detect irregular behavior using indicators such as timestamp frequency, error messages, temperature changes, signal variations, or resource usage. Students can freely choose the application domain, for example smart devices, environmental sensors, robotics, small server nodes, or industrial monitoring. A Bachelor thesis may compare lightweight machine learning models for anomaly detection. A Master thesis may investigate TinyML, online learning, model compression, or hybrid signal-processing and AI-based detection methods.
Benchmarking AI Models for Resource-Aware System MonitoringApply
This thesis focuses on benchmarking different AI models for monitoring tasks under resource constraints. The student will compare models not only based on accuracy, but also based on runtime, memory usage, energy consumption, inference latency, and deployment complexity. The monitoring task may involve anomaly detection, failure prediction, log classification, sensor analysis, or workload prediction. The project gives students freedom to select the models, datasets, and evaluation environment. A Bachelor thesis may compare a small number of models for one monitoring task. A Master thesis may design a more systematic benchmarking framework and propose guidelines for selecting models based on system constraints.
Theses
- Implementation of a Liquid Neural Network Control System for Multi-Joint Cyber Physical ARM, Michael Bidollahkhani (Master's Thesis), Advisors: Ferhat Atasoy, Abdellatef Hamdan, 2023-06, BibTeX
- Extract and mining government services, especially USO and their impacts on the development of rural communities using data mining algorithms and artificial intelligence, Michael Bidollahkhani (Bachelor's Thesis), Advisors: I. Soleimani, A. Shahbahrami, 2016, BibTeX
Publications
2026
- Poster: Resilient HPC Operations through Observability-Aware Predictive Maintenance (Michael Bidollahkhani), NHR Conference 2026 - HPC-Driven Decision Science: Optimization, Simulation, and AI for Economics and Management, Heinz Nixdorf MuseumsForum, Paderborn, Germany, 2026-09-14 BibTeX URL
- Access to AI, Beyond a Liberty (Meisa Kamyab, Michael Bidollahkhani, Julian M. Kunkel), In Proceedings of the 2nd International Conference on Sustainability, Innovation, and Society, ICSIS-26, Valencia, Spain, 2026-06 BibTeX
- When GPUs Fail Quietly: Observability-Aware Early Warning Beyond Numeric Telemetry (Michael Bidollahkhani, Freja Nordsiek, Julian M. Kunkel), arXiv (2603.28781), arXiv, 2026-03-17 BibTeX URL DOI
- AI-Powered Smart Cities (Michael Bidollahkhani), In From Smart Cities to the Metaverse, pp. 35-50, Taylor & Francis, 2026 BibTeX URL
- DECICE: AI-Driven Scheduling and Digital Twin Integration for the Cloud-HPC-Edge Compute Continuum (Aasish Kumar Sharma, Felix Stein, Mirac Aydin, Michael Bidollahkhani, Sachin P. Nanavati, Mohsen Seyedkazemi Ardebili, Giorgi Mamulashvili, Mojtaba Akbari, Jonathan Decker, Zoya Masih, Julian M. Kunkel), In Proceedings of the IEEE Computers, Software, and Applications Conference 2026, IEEE, IEEE, COMPSAC-26, Madrid, Spain, 2026 BibTeX URL
- Architectures, Learning Loops, and Emergence in Agentic Services Computing (Sadaf Shafi, Michael Bidollahkhani, Julian Kunkel), In Proceedings of the 14th IEEE International Workshop on Architecture, Design, Deployment, and Management of Networks and Applications, IEEE, IEEE, ADMNET-26, Madrid, Spain, 2026 BibTeX
- Design and Implementation of Integrated AI Scheduler for Dynamic Cloud Workloads Allocation in Kubernetes Environments (Michael Bidollahkhani, Aasish K. Sharma, Sachin P. Nanavati, Mohsen Seyedkazemi Ardebili, Giorgi Mamulashvili, Mirac Aydin, Felix Stein, Mojtaba Akbari, Julian M. Kunkel), In Proceedings of the Future Technologies Conference (FTC) 2025, Volume 1, Lecture Notes in Networks and Systems, pp. 398-420, (Editors: Kohei Arai), Springer Nature Switzerland (Cham, Switzerland), Future Technologies Conference, FTC, ISBN: 978-3-032-07986-2, 2026 BibTeX DOI
2025
- A Review on Offline Localization Strategies Using Swarm Intelligence Focusing on Belief Propagation and Internet of Vehicles (IoV) (Michael Bidollahkhani, Ossama Bin Raza, Pınar Haskul, Parisa Memarmoshrefi), In Proceedings of the 4th International Conference on Advanced Technologies, Computer Engineering and Science, ICATCES-25, Safranbolu, Türkiye, 2025-05 BibTeX DOI
- AI Work Quantization Model: Closed-System AI Computational Effort Metric (Aasish Kumar Sharma, Michael Bidollahkhani, Julian Martin Kunkel), In arXiv preprint arXiv:2503.14515, 2025-03-12 BibTeX URL
2024
- D2.4 Integrated AI-Scheduler Prototype (Michael Bidollahkhani, Aasish Kumar Sharma, Sachin Prakash Nanavati), DECICE Project Deliverable (D2.4), Zenodo, 2024-11-30 BibTeX URL DOI
- Poster: Predictive Maintenance in Server Farms with Time Series Analysis (Michael Bidollahkhani, Julian Kunkel), 2nd NHRConference 2024 at NHR4CES@TUDarmstadt, Darmstadt, Germany, 2024-09-09 BibTeX URL PDF
- HOSHMAND: Accelerated AI-Driven Scheduler Emulating Conventional Task Distribution Techniques for Cloud Workloads (Michael Bidollahkhani, Aasish Kumar Sharma, Julian Kunkel), IEEE Computers, Software, and Applications Conference, pp. 1-8, IEEE, IEEE, COMPSAC 2024, 2024-07 BibTeX
- Distracted AI: Integrating Neuroscience-Inspired Attention and Distraction Learning in ANN (Michael Bidollahkhani, M. Raahemi, P. Haskul), 2024 20th CSI International Symposium on Artificial Intelligence and Signal Processing, pp. 1-8, IEEE, IEEE, AISP, 2024-02 BibTeX DOI
- D2.3 AI Scheduler Prototypes for Storage and Compute (Michael Bidollahkhani, Aasish Kumar Sharma), Project Deliverable (D2.3), Zenodo, 2024-01-04 BibTeX URL DOI
- Comparing Fault-tolerance in Kubernetes and Slurm in HPC Infrastructure (Mirac Aydin, Michael Bidollahkhani, Julian Kunkel), Proceedings of the 18th International Conference on Advanced Computing (ADVCOMP 2024), pp. 40-49, Venice, Italy, ISSN: 2308-4499. ISBN: 978-1-68558-184-8, 2024 BibTeX URL
- Revolutionizing system reliability: The role of AI in predictive maintenance strategies (Michael Bidollahkhani, Julian Kunkel), IARIA CloudComputing 2024 Conference, pp. 1-9, Venice, Italy, ISSN: 2308-4294. ISBN: 978-1-68558-156-5, 2024 BibTeX URL
- Appreciated Team – Among Best Projects in IT for Law (ReMeP24 Hackathon): RAGdoll (Mohamed Reda Arsalan, Michael Bidollahkhani, Samanda Kortoçi, Mohammad Hamed Pakizehdel, Katja Breitenfelder, Nhu An Trinh), Hackathon / Research Achievement (ReMeP24), Ministry of Justice (Vienna, Austria), 2024 BibTeX URL
- RAGdoll AI Risk Assessment System (Mohamed Reda Arsalan, Michael Bidollahkhani, Samanda Kortoçi, Mohammad Hamed Pakizehdel, Katja Breitenfelder, Nhu An Trinh), Project / Prototype (RAGdoll), Georg-August University of Göttingen (with LIPIT Program & GWDG) (Göttingen, Germany), 2024 BibTeX URL
2023
- LTC-SE: Expanding the Potential of Liquid Time-Constant Neural Networks for Scalable AI and Embedded Systems (Michael Bidollahkhani, Ferhat Atasoy, Hamdan Abdellatef), In arXiv preprint arXiv:2304.08691, 2023-04-18 BibTeX
- A Novel Approach for Muscle Fatigue Disorders Detection Using EMG Based Time-Constant Neural Networks (Michael Bidollahkhani, F. Atasoy), In Gazi Journal of Engineering Sciences (2), 2023 BibTeX URL
- LoRaline: A Critical Message Passing Line of Communication for Anomaly Mapping in IoV Systems (Michael Bidollahkhani, O. Dakkak, A. S. M. Alajeeli, B. S. Kim), In IEEE Access (11), pp. 18107-18120, 2023 BibTeX
- Real-Time Building Management System Visual Anomaly Detection Using Heat Points Motion Analysis Machine Learning Algorithm (Michael Bidollahkhani, Isa Avci), In Tehnički vjesnik (30), pp. 318–323, 2023 BibTeX
- GENIE-NF-AI: Identifying Neurofibromatosis Tumors using Liquid Neural Network (LTC) trained on AACR GENIE Datasets (Michael Bidollahkhani, Ferhat Atasoy, Elnaz Abedini, Ali Davar, Omid Hamza, Fırat Sefaoğlu, Amin Jafari, Muhammed Nadir Yalçın, Hamdan Abdellatef), In arXiv preprint arXiv:2304.13429, 2023 BibTeX URL
- Liquid Time-Constant Neural Networks (Michael Bidollahkhani), In Interdisciplinary Artificial Intelligence, Series: Nobel Scientific Works, Edition: 1, pp. 163 (Turkey), 2023 BibTeX URL
- SIVI ZAMAN SABİTLİ SİNİR AĞI (Michael Bidollahkhani, Ferhat Atasoy), In DİSİPLİNLERARASI YAPAY ZEKÂ ARAŞTIRMALARI, Edition: 1, pp. 163-179, Nobel Yayıncılık (Ankara, Türkiye), ISBN: 978-625-398-981-1, 2023 BibTeX URL
2018
- The Neural Connection Spot (Michael Bidollahkhani, S. Darbarpanah), The International Conference on New Horizons in the Engineering Science, Istanbul, Turkey, 2018 BibTeX
- The RPAT Algorithm for Politician Assessment and Evaluation (Michael Bidollahkhani, F. Bidollahkhani), The International Conference on New Horizons in the Engineering Science, Istanbul, Turkey, 2018 BibTeX
2017
- Parallel programming Application on Medical Image Processing: MRI contours matching algorithm based on GPU accelerated methods for Tumor differential Analysis (Michael Bidollahkhani), International Congress on Science and Engineering, Hamburg, Germany, 2017 BibTeX
- Subjects Extraction and text data classification by CHERNOFF algorithm and implementation with Java general-purpose computer programming language (Michael Bidollahkhani, M. F. Masouleh), IEEE Second National and First International Conference on Soft Computing, IEEE, IEEE, Guilan, Iran, 2017 BibTeX
2015
- Optimization of Artificial Retina implant's vision (Michael Bidollahkhani, S. Darbarpanah), International Conference on Science and Engineering of Istanbul Technical University (ITU), Istanbul Technical University, Istanbul, Iran, 2015 BibTeX
2014
- A Survey on Different Strategies on Preparing Data for Data Mining (Michael Bidollahkhani, M. F. Masouleh), ISC National conference on Soft computing at Guilan technical university, Guilan technical university, Guilan, Iran, 2014 BibTeX
Talks
2026
- DAYA: Data-Aware Agentic AI Architecture for Decision-Oriented Analytics on HPC Systems (Michael Bidollahkhani, Orr Shomroni), NHR Conference 2026 - HPC-Driven Decision Science: Optimization, Simulation, and AI for Economics and Management, Heinz Nixdorf MuseumsForum, Paderborn, Germany, 2026-09-15
- GWDG AI Services and Requirements for a Scientific AI Service (Michael Bidollahkhani), Bremen AI School, Bremen, Germany, 2026-08-19
- Research Exchange at the Cambridge University Press Booth (Michael Bidollahkhani), IJCAI-ECAI 2026, Congress Centrum Bremen, Bremen, Germany, 2026-08-18
2025
- Design and Implementation of Integrated AI Scheduler for Dynamic Cloud Workloads Allocation in Kubernetes Environments (Michael Bidollahkhani), Future Technologies Conference (FTC 2025), Munich, Germany, 2025-11-06
2024
- Integrated AI-Scheduler Prototype (Michael Bidollahkhani, Sachin Prakash Nanavati), DECICE - D2.4 Integrated AI-Scheduler Prototype, EU DECICE Project Seminar, 2024-11-30
- Predictive Maintenance in Server Farms with Time Series Analysis (Michael Bidollahkhani), 2nd NHR Conference 2024 at NHR4CES@TU Darmstadt - Poster Presentation, TU Darmstadt, Darmstadt, Germany, 2024-09-09
- HOSHMAND: Accelerated AI-Driven Scheduler Emulating Conventional Task Distribution Techniques for Cloud Workloads (Michael Bidollahkhani), 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC 2024), Osaka, Japan, 2024-07-04
- Revolutionizing System Reliability: The Role of AI in Predictive Maintenance Strategies (Awarded Presentation) (Michael Bidollahkhani), CLOUD COMPUTING 2024 - The Fifteenth International Conference on Cloud Computing, GRIDs, and Virtualization, Venice, Italy, 2024-04-14
- Distracted AI: Integrating Neuroscience-Inspired Attention and Distraction Learning in ANN (Michael Bidollahkhani, Pınar Haskul, Maryam Raahemi), 2024 20th CSI International Symposium on Artificial Intelligence and Signal Processing (AISP 2024), Babol, Iran, 2024-02-21
- AI Scheduler Prototypes for Storage and Compute (Michael Bidollahkhani, Aasish Kumar Sharma), DECICE - D2.3 AI Scheduler Prototypes for Storage and Compute, EU DECICE Project Seminar, 2024-01-04
View Profile →
https://synchange.com
Visit Synchange Website →
View Profile →
All publications as BibTex