Next Article in Journal
Evaluation of Multivariate Adaptive Regression Splines and Artificial Neural Network for Prediction of Mean Sea Level Trend around Northern Australian Coastlines
Previous Article in Journal
Conceptual Coverage Driven by Essential Concepts: A Formal Concept Analysis Approach
Previous Article in Special Issue
Chaos on Fuzzy Dynamical Systems
Article

Towards Optimal Supercomputer Energy Consumption Forecasting Method

IT4Innovations, VSB—Technical University of Ostrava, 17.listopadu 2172/15, 70833 Ostrava-Poruba, Czech Republic
Academic Editor: António M. Lopes
Mathematics 2021, 9(21), 2695; https://doi.org/10.3390/math9212695
Received: 14 September 2021 / Revised: 17 October 2021 / Accepted: 18 October 2021 / Published: 23 October 2021
(This article belongs to the Special Issue Dynamical Systems and Their Applications Methods)
Accurate prediction methods are generally very computationally intensive, so they take a long time. Quick prediction methods, on the other hand, are not very accurate. Is it possible to design a prediction method that is both accurate and fast? In this paper, a new prediction method is proposed, based on the so-called random time-delay patterns, named the RTDP method. Using these random time-delay patterns, this method looks for the most important parts of the time series’ previous evolution, and uses them to predict its future development. When comparing the supercomputer infrastructure power consumption prediction with other commonly used prediction methods, this newly proposed RTDP method proved to be the most accurate and the second fastest. View Full-Text
Keywords: forecasting; prediction method; time series; random time delays patterns; zeroth algorithm; machine learning; statistical; supercomputer power consumption; complex system forecasting; prediction method; time series; random time delays patterns; zeroth algorithm; machine learning; statistical; supercomputer power consumption; complex system
Show Figures

Figure 1

MDPI and ACS Style

Tomčala, J. Towards Optimal Supercomputer Energy Consumption Forecasting Method. Mathematics 2021, 9, 2695. https://doi.org/10.3390/math9212695

AMA Style

Tomčala J. Towards Optimal Supercomputer Energy Consumption Forecasting Method. Mathematics. 2021; 9(21):2695. https://doi.org/10.3390/math9212695

Chicago/Turabian Style

Tomčala, Jiří. 2021. "Towards Optimal Supercomputer Energy Consumption Forecasting Method" Mathematics 9, no. 21: 2695. https://doi.org/10.3390/math9212695

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop