Increasing the energy efficiency of a data center based on machine learning

Abstract

Energy efficiency of data centers (DCs) is of great concern due to their large amount of energy consumption and the foreseeable growth in the demand of digital services in the future. The past decade witnessed improvements of the energy efficiency of DCs from an extensive margin—a shift from small to large, more efficient DCs. Improvements from the intensive margin, that is, from more efficient operation, would be critical in limiting the energy consumption and environmental impact of DCs in the upcoming period. Machine learning algorithms have advantages in optimizing the operation of DCs to improve energy efficiency as they have shown the potential of discovering control strategies not found by traditional method, and producing working condition‐dependent control strategies. This study proposes ready‐to‐use machine learning methods with practical details to decrease the most commonly used energy efficiency metric—power usage effectiveness in DCs. We achieved an accurate prediction by properly selecting the features used in the proposed prediction models established by neural network, light gradient boosting machine, recurrent neural network, and random forests. The proposed approaches are implemented in one of the largest hyperscale DCs in China—Tencent Tianjin DC, to optimize the set points of controllable variables in the cooling system and to detect and adjust the unreasonable working conditions in the modular data centers. The lower bound of PUE reduction was 0.005 with the proposed approaches, leading to about 1500 MWh (0.24% of the total designed electricity consumption of this DC) of energy saved per year in this hyperscale DC. The proposed methods have the potential to be transferred to DCs of similar scale, and the framework of our work could serve as a guide for machine learning‐based optimization of environmental indicators in other complex product/service systems.

Data innovation in industrial ecology

“…Entire industrial sectors are digitizing, and the papers of this special issue sample the contours of this transition and its implications for the application of IE principles. Yang et al (2021) demonstrate the gains in energy efficiency that can be achieved in data centers through the use of machine learning. Liao et al (2021) surveyed and categorized the types of AI applications in the chemical industry and their sustainability implications.…”

AI for Automating Data Center Operations: Model Explainability in the Data Centre Context Using Shapley Additive Explanations (SHAP)

“…Research by Bianchini, R. et al has implemented an XGB tree-based model for efficient resource and workload management towards ml-centric cloud platforms [2]. Other efforts include research by Haghshenas et al [3] that utilized a multi-agent machine learning (ML) strategy for energy-efficient virtual server consolidation and a study by Z. Yang et al [11] that implemented a light gradient boosting machine, a recurrent neural network, and random forests to optimize the energy efficiency of the total input energy per year of a DC by 0.24%. Another study [12,13] utilized machine learning thermal modeling to enhance DC energy efficiency, and many more efforts have been implemented to automate and optimize DC operations.…”

Edge Data Center Organization and Optimization by Using Cage Graphs

“…This situation is bringing more attention to data center organization and optimization [2] in order to improve their performance in IoT environments [3]. In this context, machine learning techniques may help optimize performance by achieving increased efficiency in resource usage [4], leading to a decrease in energy consumption [5], which may lower the carbon footprint [6] in order to make the IoT environments more sustainable [7] and resilient [8].…”