Generalizable Machine Learning Models for Predicting Data Center Server Power, Efficiency, and Throughput

• URL: http://arxiv.org/abs/2503.06439v1
• Date: Sun, 09 Mar 2025 04:39:53 GMT
• Title: Generalizable Machine Learning Models for Predicting Data Center Server Power, Efficiency, and Throughput
• Authors: Nuoa Lei, Arman Shehabi, Jun Lu, Zhi Cao, Jonathan Koomey, Sarah Smith, Eric Masanet,
• Abstract summary: This study employs a machine learning-based approach, using the SPECPower_ssj2008 database, to facilitate user-friendly and generalizable server modeling.<n>The resulting models demonstrate high accuracy, with errors falling within approximately 10% on the testing dataset, showcasing their practical utility and generalizability.
• Score: 5.0170620956513465
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the rapidly evolving digital era, comprehending the intricate dynamics influencing server power consumption, efficiency, and performance is crucial for sustainable data center operations. However, existing models lack the ability to provide a detailed and reliable understanding of these intricate relationships. This study employs a machine learning-based approach, using the SPECPower_ssj2008 database, to facilitate user-friendly and generalizable server modeling. The resulting models demonstrate high accuracy, with errors falling within approximately 10% on the testing dataset, showcasing their practical utility and generalizability. Through meticulous analysis, predictive features related to hardware availability date, server workload level, and specifications are identified, providing insights into optimizing energy conservation, efficiency, and performance in server deployment and operation. By systematically measuring biases and uncertainties, the study underscores the need for caution when employing historical data for prospective server modeling, considering the dynamic nature of technology landscapes. Collectively, this work offers valuable insights into the sustainable deployment and operation of servers in data centers, paving the way for enhanced resource use efficiency and more environmentally conscious practices.

Related papers

• Using Federated Machine Learning in Predictive Maintenance of Jet Engines [0.0]
  This paper aims to predict the Remaining Useful Life (RUL) of turbine jet engines using a federated machine learning framework.<n>The system aims to capture complex computation and patterns in the engine data to enhance the accuracy of RUL predictions.
  arXiv  Detail & Related papers  (2025-02-07T20:41:36Z)
• From Machine Learning to Machine Unlearning: Complying with GDPR's Right to be Forgotten while Maintaining Business Value of Predictive Models [9.380866972744633]
  This work develops a holistic machine learning-to-unlearning framework, called Ensemble-based iTerative Information Distillation (ETID)<n>ETID incorporates a new ensemble learning method to build an accurate predictive model that can facilitate handling data erasure requests.<n>We also introduce an innovative distillation-based unlearning method tailored to the constructed ensemble model to enable efficient and effective data erasure.
  arXiv  Detail & Related papers  (2024-11-26T05:42:46Z)
• Computation-efficient Deep Learning for Computer Vision: A Survey [121.84121397440337]
  Deep learning models have reached or even exceeded human-level performance in a range of visual perception tasks. Deep learning models usually demand significant computational resources, leading to impractical power consumption, latency, or carbon emissions in real-world scenarios. New research focus is computationally efficient deep learning, which strives to achieve satisfactory performance while minimizing the computational cost during inference.
  arXiv  Detail & Related papers  (2023-08-27T03:55:28Z)
• Bringing AI to the edge: A formal M&S specification to deploy effective IoT architectures [0.0]
  The Internet of Things is transforming our society, providing new services that improve the quality of life and resource management. These applications are based on ubiquitous networks of multiple distributed devices, with limited computing resources and power. New architectures such as fog computing are emerging to bring computing infrastructure closer to data sources.
  arXiv  Detail & Related papers  (2023-05-11T21:29:58Z)
• On Efficient Training of Large-Scale Deep Learning Models: A Literature Review [90.87691246153612]
  The field of deep learning has witnessed significant progress, particularly in computer vision (CV), natural language processing (NLP), and speech. The use of large-scale models trained on vast amounts of data holds immense promise for practical applications. With the increasing demands on computational capacity, a comprehensive summarization on acceleration techniques of training deep learning models is still much anticipated.
  arXiv  Detail & Related papers  (2023-04-07T11:13:23Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)
• FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server [64.94942635929284]
  Federated Learning (FL) suffers from two critical challenges, i.e., limited computational resources and low training efficiency. We propose a novel FL framework, FedDUAP, to exploit the insensitive data on the server and the decentralized data in edge devices. By integrating the two original techniques together, our proposed FL model, FedDUAP, significantly outperforms baseline approaches in terms of accuracy (up to 4.8% higher), efficiency (up to 2.8 times faster), and computational cost (up to 61.9% smaller)
  arXiv  Detail & Related papers  (2022-04-25T10:00:00Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• Characterization and Prediction of Deep Learning Workloads in Large-Scale GPU Datacenters [30.952491139350908]
  We present a comprehensive study about the characteristics of Deep Learning jobs and resource management. We introduce a general-purpose framework, which manages resources based on historical data. As case studies, we design: a Quasi-Shortest-Service-First scheduling service, which can minimize the cluster-wide average job completion time by up to 6.5x; and a Cluster Energy Saving service, which improves overall cluster utilization by up to 13%.
  arXiv  Detail & Related papers  (2021-09-03T05:02:52Z)
• Power Modeling for Effective Datacenter Planning and Compute Management [53.41102502425513]
  We discuss two classes of statistical power models designed and validated to be accurate, simple, interpretable and applicable to all hardware configurations and workloads. We demonstrate that the proposed statistical modeling techniques, while simple and scalable, predict power with less than 5% Mean Absolute Percent Error (MAPE) for more than 95% diverse Power Distribution Units (more than 2000) using only 4 features.
  arXiv  Detail & Related papers  (2021-03-22T21:22:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.