Optimization air-conditioning system and thermal management of data center via fan-wall free cooling technology

Zhang, Jun; Mao, Ruiyong; Li, Chao; Jiang, Lan; Yi, Xiaoyan; Zhang, Zujing

doi:10.1016/j.applthermaleng.2023.121245

Cited by 8 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This capacity for 'learning' positions machine learning as a powerful tool for predicting data center behaviors, optimizing cooling strategies, and even automating certain aspects of data center management. Machine learning, especially techniques like neural networks, has shown promise in various predictive tasks due to its ability to handle large datasets and complex non-linear relationships [17][18][19]. This makes it particularly suited to address the intricate dynamics of data center environments where numerous factors-like server workloads, external temperatures, and cooling system states-interact in multifaceted ways.…”

Section: Introductionmentioning

confidence: 99%

Computational Engineering based approach on Artificial Intelligence and Machine learning-Driven Robust Data Centre for Safe Management

et al. 2023

JMC

View full text Add to dashboard Cite

This research explores the integration of Artificial Intelligence (AI), specifically the Recurrent Neural Network (RNN) model, into the optimization of data center cooling systems through Computational Engineering. Utilizing Computational Fluid Dynamics (CFD) simulations as a foundational data source, the study aimed to enhance operational efficiency and sustainability in data centers through predictive modeling. The findings revealed that the RNN model, trained on CFD datasets, proficiently forecasted key data center conditions, including temperature variations and airflow dynamics. This AI-driven approach demonstrated marked advantages over traditional methods, significantly minimizing energy wastage commonly incurred through overcooling. Additionally, the proactive nature of the model allowed for the timely identification and mitigation of potential equipment challenges or heat hotspots, ensuring uninterrupted operations and equipment longevity. While the research showcased the transformative potential of merging AI with data center operations, it also indicated areas for further refinement, including the model's adaptability to diverse real-world scenarios and its management of long-term dependencies. In conclusion, the study illuminates a promising avenue for enhancing data center operations, highlighting the significant benefits of an AI-driven approach in achieving efficiency, cost reduction, and environmental sustainability.

show abstract

Section: Introductionmentioning

confidence: 99%