---
_id: '63399'
abstract:
- lang: eng
  text: Data centers (DCs) form the backbone of our growing digital economy, but their
    rising energy demands pose challenges to our environment. At the same time, reusing
    waste heat from DCs also represents an opportunity, for example, for more sustainable
    heating of residential buildings. Modeling and optimizing these coupled and dynamic
    systems of heat generation and reuse is complex. On the one hand, physical simulations
    can be used to model these systems, but they are time-consuming to develop and
    run. Machine learning (ML), on the other hand, allows efficient data-driven modeling,
    but conventional correlation-based approaches struggle with the prediction of
    interventions and out-of-distribution generalization. Recent advances in causal
    ML, which combine principles from causal inference with flexible ML methods, are
    a promising approach for more robust predictions. Due to their focus on modeling
    interventions and cause-and-effect relationships, it is difficult to evaluate
    causal ML approaches rigorously. To address this challenge, we built a testbed
    of a miniature DC with an integrated waste heat network, equipped with sensors
    and actuators. This testbed allows conducting controlled experiments and automatic
    collection of realistic data, which can then be used to benchmark conventional
    and causal ML methods. Our experimental results highlight the strengths and weaknesses
    of each modeling approach, providing valuable insights on how to appropriately
    apply different types of machine learning to optimize data center operations and
    enhance their sustainability.
author:
- first_name: David Zapata
  full_name: Gonzalez, David Zapata
  last_name: Gonzalez
- first_name: Marcel
  full_name: Meyer, Marcel
  last_name: Meyer
- first_name: Oliver
  full_name: Müller, Oliver
  last_name: Müller
citation:
  ama: 'Gonzalez DZ, Meyer M, Müller O. Causal Machine Learning Approaches for Modelling
    Data Center Heat Recovery: A Physical Testbed Study. In: <i>ACM SIGEnergy Energy
    Informatics Review</i>. Vol 5. Association for Computing Machinery (ACM); 2025:4-10.
    doi:<a href="https://doi.org/10.1145/3757892.3757893">10.1145/3757892.3757893</a>'
  apa: 'Gonzalez, D. Z., Meyer, M., &#38; Müller, O. (2025). Causal Machine Learning
    Approaches for Modelling Data Center Heat Recovery: A Physical Testbed Study.
    <i>ACM SIGEnergy Energy Informatics Review</i>, <i>5</i>(2), 4–10. <a href="https://doi.org/10.1145/3757892.3757893">https://doi.org/10.1145/3757892.3757893</a>'
  bibtex: '@inproceedings{Gonzalez_Meyer_Müller_2025, title={Causal Machine Learning
    Approaches for Modelling Data Center Heat Recovery: A Physical Testbed Study},
    volume={5}, DOI={<a href="https://doi.org/10.1145/3757892.3757893">10.1145/3757892.3757893</a>},
    number={2}, booktitle={ACM SIGEnergy Energy Informatics Review}, publisher={Association
    for Computing Machinery (ACM)}, author={Gonzalez, David Zapata and Meyer, Marcel
    and Müller, Oliver}, year={2025}, pages={4–10} }'
  chicago: 'Gonzalez, David Zapata, Marcel Meyer, and Oliver Müller. “Causal Machine
    Learning Approaches for Modelling Data Center Heat Recovery: A Physical Testbed
    Study.” In <i>ACM SIGEnergy Energy Informatics Review</i>, 5:4–10. Association
    for Computing Machinery (ACM), 2025. <a href="https://doi.org/10.1145/3757892.3757893">https://doi.org/10.1145/3757892.3757893</a>.'
  ieee: 'D. Z. Gonzalez, M. Meyer, and O. Müller, “Causal Machine Learning Approaches
    for Modelling Data Center Heat Recovery: A Physical Testbed Study,” in <i>ACM
    SIGEnergy Energy Informatics Review</i>, 2025, vol. 5, no. 2, pp. 4–10, doi: <a
    href="https://doi.org/10.1145/3757892.3757893">10.1145/3757892.3757893</a>.'
  mla: 'Gonzalez, David Zapata, et al. “Causal Machine Learning Approaches for Modelling
    Data Center Heat Recovery: A Physical Testbed Study.” <i>ACM SIGEnergy Energy
    Informatics Review</i>, vol. 5, no. 2, Association for Computing Machinery (ACM),
    2025, pp. 4–10, doi:<a href="https://doi.org/10.1145/3757892.3757893">10.1145/3757892.3757893</a>.'
  short: 'D.Z. Gonzalez, M. Meyer, O. Müller, in: ACM SIGEnergy Energy Informatics
    Review, Association for Computing Machinery (ACM), 2025, pp. 4–10.'
date_created: 2025-12-22T13:17:36Z
date_updated: 2025-12-22T13:18:19Z
doi: 10.1145/3757892.3757893
intvolume: '         5'
issue: '2'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://dl.acm.org/doi/abs/10.1145/3757892.3757893
oa: '1'
page: 4-10
publication: ACM SIGEnergy Energy Informatics Review
publication_identifier:
  issn:
  - 2770-5331
  - 2770-5331
publication_status: published
publisher: Association for Computing Machinery (ACM)
status: public
title: 'Causal Machine Learning Approaches for Modelling Data Center Heat Recovery:
  A Physical Testbed Study'
type: conference
user_id: '105506'
volume: 5
year: '2025'
...