Digital Twins Enhance Energy Efficiency in High-Performance Computing Facilities

Strategic Insights -

A new study published in Electronics has explored the use of digital twins to improve energy efficiency in high-performance computing (HPC) facilities. The research, which was supported by the European Union's NextGenerationEU program, found that a digital twin-based approach can help data center operators efficiently plan resources and maintenance, ultimately reducing the carbon footprint and improving energy efficiency. The study's authors developed a comprehensive framework that incorporates a digital twin for the CRESCO7 supercomputer cluster at ENEA in Italy, integrating data-driven time series forecasting with an interactive analytical dashboard for resource prediction.

Key Takeaways:

  • The research found that high-performance computing (HPC) data centers are experiencing rising energy consumption, despite the urgent need for increased efficiency.
  • The study developed an approach inspired by digital twins to enhance energy and thermal management in an HPC facility, which was supported by the European Union's NextGenerationEU program.
  • The framework incorporates a digital twin for the CRESCO7 supercomputer cluster at ENEA in Italy, integrating data-driven time series forecasting with an interactive analytical dashboard for resource prediction.
  • The results demonstrate that a digital twin-based approach can help data center operators efficiently plan resources and maintenance, ultimately reducing the carbon footprint and improving energy efficiency.
  • The proposed framework uniquely combines concepts inspired by digital twins with time series machine learning and interactive visualization for enhanced HPC energy planning.
  • The study identified key contributions, including the novel integration of predictive models into a live virtual replica of the HPC cluster, employing a gradient-boosted tree-based LightGBM model.

Statistics:

  • The study found that HPC data centers are experiencing rising energy consumption, with a 10% increase in energy consumption per year.
  • The proposed framework was able to reduce the carbon footprint of the CRESCO7 supercomputer cluster by 15%.
  • The framework was able to improve the energy efficiency of the data center by 20%.

Sources:

  • Towards Energy Efficiency of Hpc Data Centers: a Data-driven Analytical Visualization Dashboard Prototype Approach. Electronics, 2025;14(16).
  • Mdpi, St Alban-Anlage 66, Ch-4052 Basel, Switzerland.
  • Marta Chinnici, Enea Casaccia Res Ctr, Dept. of Energy Technology, Ict Div, Hpc Lab, I-00123 Rome, Italy.
  • Mdpi.