Cloud resource prediction model based on triple exponential smoothing method and temporal convolutional network

Xie, Xiaolan, Zhang, Zhenzheng, Wang, Jianwei and Cheng, Xiaochun ORCID: https://orcid.org/0000-0003-0371-9646 (2019) Cloud resource prediction model based on triple exponential smoothing method and temporal convolutional network. Journal on Communications, 40 (8) . pp. 143-150. ISSN 1000-436X [Article] (doi:10.11959/j.issn.1000-436x.2019172)

[img] PDF - Published version (with publisher's formatting)
Restricted to Repository staff and depositor only

Download (912kB)

Abstract

The container cloud represented by Docker and Kubernetes has the advantages of less additional resource overhead and shorter start-up and destruction time.However there are still resource management issues such as over-supply and under-supply.In order to allow the Kubernetes cluster to respond “in advance” to the resource usage of the applications deployed on it,and then to schedule and allocate resources in a timely,accurate and dynamic manner based on the predicted value,a cloud resource prediction model based on triple exponential smoothing method and temporal convolutional network was proposed,based on historical data to predict future demand for resources.To find the optimal combination of parameters,the parameters were optimized using TPOT thought.Experiments on the CPU and memory of the Google dataset show that the model has better prediction performance than other models.

Item Type: Article
Keywords (uncontrolled): resource prediction, Kubernetes, exponential smoothing method, temporal convolutional network
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 29525
Notes on copyright: Copyright © 2018 Journal on Communications, All Rights Reserved.
Useful Links:
Depositing User: Xiaochun Cheng
Date Deposited: 12 Mar 2020 16:12
Last Modified: 12 Mar 2020 16:12
URI: https://eprints.mdx.ac.uk/id/eprint/29525

Actions (login required)

View Item View Item

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year