ENNP: an enhanced neural networks-based power consumption prediction algorithm to deep learning-based workloads on AI-enabled data centers

The traditional power consumption prediction algorithms are no longer suitable for deep learning-based workloads owing to the long-term dependencies and highly volatile nature of power usage in such applications. To address these challenges, this study proposes ENNP, an enhanced neural network-based...

Full description

Saved in:
Bibliographic Details
Published in:Cluster computing Vol. 29; no. 1; p. 36
Main Authors: Wang, Hengdong, Jing, Chao
Format: Journal Article
Language:English
Published: New York Springer US 01.02.2026
Springer Nature B.V
Subjects:
Accuracy
Algorithms
Anomalies
Bayesian analysis
Computer centers
Computer Communication Networks
Computer Science
Data centers
Deep learning
Machine learning
Natural language processing
Neural networks
Operating Systems
Optimization
Power consumption
Prediction models
Processor Architectures
Time series
Workload
Workloads
Power consumption prediction
KAN
AI-enabled data centers
TimeMixer
LSTM
Bayesian optimization
ISSN:1386-7857, 1573-7543
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The traditional power consumption prediction algorithms are no longer suitable for deep learning-based workloads owing to the long-term dependencies and highly volatile nature of power usage in such applications. To address these challenges, this study proposes ENNP, an enhanced neural network-based power consumption prediction algorithm for deep learning-based workloads in AI-enabled data centers. In general, ENNP inherits the advantages of the TimeMixer framework in mitigating model overfitting. However, direct application of TimeMixer does not provide the flexibility needed to handle complex power consumption patterns. To overcome this limitation, ENNP integrates three key techniques: Bayesian optimization, KAN, and LSTM, to maximize the predictive performance of TimeMixer. Specifically, (1) Bayesian optimization is employed for parameter selection and extraction of multiscale time series; (2) KAN is utilized to reconstruct multiscale time series; and (3) an improved LSTM is adopted to predict on multiscale time series and fusing these predictions to obtain the final prediction. Finally, experiments were conducted on real CPU/GPU servers using trace data collected from various deep learning workloads, including natural language processing, image recognition, multivariable prediction, and anomaly detection jobs. The experimental results show that ENNP achieves the best performance compared with other well-known prediction algorithms such as BP, LSTM, and MLR, as well as recent general time-series prediction models, with a maximum improvement of 38.29% in accuracy.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1386-7857
1573-7543
DOI:10.1007/s10586-025-05840-w