DC4 — Carbon-Aware Digital Twins for Flexible EDCs

Host: TU Wien, Vienna, Austria — High-Performance Computing Systems group, Institute of Information Systems Engineering.
Work package: WP1 (Programmable Energy-Integrated Infrastructure)
Duration and start: 36 months, full-time; start between February and September 2027 (latest start September 2027).

The project

A datacenter’s flexibility is hard to use safely without one model that captures how its computing, electrical, and thermal parts behave together. In this project you build that model: a multi-domain digital twin.

The digital twin will continuously compute the site’s “safe operating envelope” — a machine-readable limit that says how much power the site can change, and when, without breaking any rule. This makes the site’s flexibility both predictable and verifiable for the rest of the AEGIS platform.

What you will work on:

• Build a framework that captures the coupled dynamics across very different timescales.
• Develop a multi-fidelity modeling approach covering power electronics, compute, thermal behavior, and workload.
• Export the model as semantic views, using ontologies, so other tools can read it.

What you will deliver:

• A digital twin with measured prediction errors.
• A toolkit that computes the safe envelope and respects operational limits.
• A semantic interface (API) shown to work with fleet orchestrators.

Secondments

You will spend two research visits with partners in the network:

• WienIT (Vienna, Austria) — 4 months from around March 2028 (industry), with Martin Michalitsch: collect real-world datacenter operating data and energy measurements.
• École Polytechnique Fédérale de Lausanne (EPFL) (Lausanne, Switzerland) — 3 months from around September 2029 (academic), with David Atienza: test the carbon-aware digital twin in a real environment at EPFL’s EcoCloud.

The host

The High-Performance Computing Systems group at TU Wien’s Institute of Information Systems Engineering works on computational sustainability and energy-efficient resource allocation across the cloud continuum.

Supervision

Main supervisor: Ivona Brandić (ORCID) — Full Professor for High-Performance Computing Systems, TU Wien; leads the Computational Sustainability unit. She works on energy-efficient resource allocation across the cloud continuum.

Co-supervisors:

• Martin Michalitsch — WienIT
• David Atienza (ORCID) — EPFL

Profile we are looking for

• Modeling and simulation of cyber-physical or energy systems
• Software engineering
• Familiarity with ontologies or semantic models is a plus
• MSc (completed or near completion) in computer science, electrical engineering, or a related field
• Curiosity, initiative, and good spoken and written English

You must also meet the MSCA eligibility rules — no PhD yet, the mobility rule, and open to all nationalities.

How to apply

Official vacancy at the host institution: link coming soon.

Until then, apply through the central AEGIS application portal: AEGIS application portal (reference position DC4), and read what to include in your application.

Questions about this position? Contact the coordinator, Prof. Paul Pop, aegis@compute.dtu.dk.