The increasing energy demand of data centers poses a significant challenge for universities and public and private organizations striving to optimize energy resources and reduce environmental impact. Developing a digital twin for the Department of Computer Science data center at the University of Turin represents a strategic approach to advanced monitoring and management. Specifically, the digital twin allows for the integration of real-time data with dynamic simulations, providing an accurate virtual representation of the data center. This model enables real-time energy load analysis, temperature distribution monitoring, and the simulation of corrective actions to improve HVAC system efficiency, optimize rack layout, and reduce cooling and ventilation energy consumption. The organization of the energy model requires a precise and complex structure, beginning with the modeling of the physical components of the data center and extending to the detailed simulation of thermal flows and zone interactions. The model configuration includes creating distinct thermal zones for hot and cold aisles, racks, and plenums to accurately reflect internal thermal exchange patterns. Integration with dynamic simulation tools enables precise parameter calibration to yield accurate performance and consumption predictions and provides a safe environment to test innovative technologies without impacting physical infrastructure. A digital twin also offers substantial opportunities for predictive maintenance, allowing timely interventions to prevent failures, and reduces operational costs through the simulation of optimization scenarios. In terms of sustainability, it facilitates life cycle analysis and carbon footprint reduction. Consequently, developing a digital twin for the University of Turin data center not only enhances system reliability and sustainability but also serves as a replicable example for other similar-sized facilities.

Digital Twin Technology in University Data Centers: A Model for Operational Efficiency and Sustainability

Viviana Vaccaro
;
Lavinia Chiara Tagliabue
2025-01-01

Abstract

The increasing energy demand of data centers poses a significant challenge for universities and public and private organizations striving to optimize energy resources and reduce environmental impact. Developing a digital twin for the Department of Computer Science data center at the University of Turin represents a strategic approach to advanced monitoring and management. Specifically, the digital twin allows for the integration of real-time data with dynamic simulations, providing an accurate virtual representation of the data center. This model enables real-time energy load analysis, temperature distribution monitoring, and the simulation of corrective actions to improve HVAC system efficiency, optimize rack layout, and reduce cooling and ventilation energy consumption. The organization of the energy model requires a precise and complex structure, beginning with the modeling of the physical components of the data center and extending to the detailed simulation of thermal flows and zone interactions. The model configuration includes creating distinct thermal zones for hot and cold aisles, racks, and plenums to accurately reflect internal thermal exchange patterns. Integration with dynamic simulation tools enables precise parameter calibration to yield accurate performance and consumption predictions and provides a safe environment to test innovative technologies without impacting physical infrastructure. A digital twin also offers substantial opportunities for predictive maintenance, allowing timely interventions to prevent failures, and reduces operational costs through the simulation of optimization scenarios. In terms of sustainability, it facilitates life cycle analysis and carbon footprint reduction. Consequently, developing a digital twin for the University of Turin data center not only enhances system reliability and sustainability but also serves as a replicable example for other similar-sized facilities.
2025
2025 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP)
Torino
12-14 March 2025
2025 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP)
IEEE by The Institute of Electrical and Electronics Engineers
494
498
979-8-3315-2493-7
979-8-3315-2494-4
Viviana Vaccaro; Lavinia Chiara Tagliabue
File in questo prodotto:
File Dimensione Formato  
249300a494 (3).pdf

Accesso riservato

Tipo di file: PREPRINT (PRIMA BOZZA)
Dimensione 294.03 kB
Formato Adobe PDF
294.03 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/2109874
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact