Forschungszentrum Jülich Logo

PhD position - Learning Tailored Iterative Algorithms for Accelerating AC Power Flow Computations (HDS-LEE graduate school)

Remote
vor 3 Tagen
Jülich
Stellenbeschreibung

Shaping Change at Forschungszentrum Jülich

We are seeking a motivated individual to join the Helmholtz School for Data Science in Life, Earth and Energy (HDS-LEE) as a PhD candidate. This position is based at the Institute of Climate and Energy Systems - Energy Systems Engineering (ICE-1), focusing on the development of models and algorithms for simulating and optimizing future energy systems.

Your Role: Learning Tailored Iterative Algorithms for Accelerating AC Power Flow Computations

This project leverages machine learning (ML) to enhance the efficiency of solving AC power flow (AC-PF) computations. By learning from previously solved instances, we aim to develop ML models that can solve new, similar problems more effectively than traditional algorithms like Newton's method. This could enable real-time contingency analysis, rapid design-space exploration, and on-line operational optimization of power systems.

Your Tasks:

  • Familiarize yourself with our existing neural network superstructure for learning iterative algorithms.
  • Extend the superstructure to handle AC-PF problems of varying complexities and evaluate its convergence during inference.
  • Investigate scaling and performance bottlenecks.
  • Explore hybrid ML-classical approaches, meta-learning, and the integration of convex optimization layers.
  • Improve inference efficiency (e.g., GPU acceleration) and determine the applicability domain of learned algorithms.
  • Publish and present your findings in peer-reviewed journals and at international conferences.
  • Supervise student theses.

Your Profile:

  • Excellent Master's degree in computational engineering, mathematics, computer science, physics, engineering, or a related field with a strong academic record.
  • Solid background in numerical methods and machine learning.
  • Proficiency in at least one programming language (Python, Julia, C++, ...).
  • Strong analytical and organizational skills.
  • Ability to work independently and collaboratively.
  • Effective communication skills and interest in interdisciplinary and international teamwork.
  • Working proficiency in English.

Our Offer:

  • Opportunity to pursue a doctoral degree at RWTH Aachen University (Faculty for Mechanical Engineering) under the supervision of Prof. Alexander Mitsos.
  • Access to excellent scientific and technical infrastructure.
  • A highly motivated, international, and interdisciplinary working environment.
  • Continuous scientific mentoring from Prof. Alexander Mitsos, Prof. Uwe Naumann, and Dr. Manuel Dahmen.
  • Participation in international conferences.
  • Unique HDS-LEE graduate school program, including data science and soft skill courses, and annual retreats.
  • Opportunities for personal and professional development through comprehensive training programs and networking via JuDocS.
  • 30 days of annual leave and flexible working arrangements, including partial remote work.
  • Support services for international employees.

The position is limited to three years with a possible one-year extension. Salary is based on 75% of pay group 13 of the Collective Agreement for the Public Service (TVöD-Bund), plus a 60% special payment.

We value diversity and inclusion and encourage applications from individuals of all backgrounds.

Apply as soon as possible, as the position will remain open until filled.

For further information on doctoral degrees at Forschungszentrum Jülich, please visit: https://www.fz-juelich.de/en/careers/phd

For information on diversity and equal opportunities, visit: https://go.fz-juelich.de/equality and https://go.fz-juelich.de/womens-job-journey.