Title:
CLUSTER NODE LOAD STATE PREDICTION-BASED JOB SCHEDULING METHOD
Document Type and Number:
WIPO Patent Application WO/2020/206705
Kind Code:
A1
Abstract:
Disclosed in the present invention is a cluster node load state prediction-based job scheduling method, which belongs to the field of information technology processing. The present invention proposes a cluster node load state prediction-based job scheduling method, first the design idea of the algorithm is introduced, and cluster nodes are divided into a queue of alive nodes and a queue of sleep nodes according to the load state of a prediction algorithm; then the sleep nodes are dynamically activated according to the amount of resources required for calculation, so as to achieve the purpose of dynamically adjusting the cluster scale; thereafter, the flow of the algorithm, the steps of the algorithm and the implementation of pseudo codes of the algorithm are described, and then the energy-saving effect of the algorithm is analyzed; furthermore, an experiment verification process is introduced, comprising design of an experiment and selection of a data set, and finally, quantitative analysis is performed on an experiment result, proving that the method of the present application has an energy-saving effect in practical sense.
Inventors:
ZHANG JINQUAN (CN)
NI LINA (CN)
YU JIGUO (CN)
HAN QINGLIANG (CN)
YANG ZHENYU (CN)
ZHANG FUXIN (CN)
NI LINA (CN)
YU JIGUO (CN)
HAN QINGLIANG (CN)
YANG ZHENYU (CN)
ZHANG FUXIN (CN)
Application Number:
PCT/CN2019/082593
Publication Date:
October 15, 2020
Filing Date:
April 15, 2019
Export Citation:
Assignee:
UNIV SHANDONG SCIENCE & TECH (CN)
International Classes:
G06F9/48
Foreign References:
CN104317658A | 2015-01-28 | |||
CN103108039A | 2013-05-15 | |||
CN108874542A | 2018-11-23 | |||
US20180101313A1 | 2018-04-12 |
Other References:
GU WEI: "Dynamic Load Balancing Algorithm Using Time Series Prediction", INDUSTRIAL CONTROL COMPUTER, vol. 25, no. 12, 31 December 2012 (2012-12-31), pages 86 - 87, XP055741912
Attorney, Agent or Firm:
QINGDAO ZHIDILINGCHUANG PATENT AGENCY CO., LTD (CN)
Download PDF: