Title:
USING MACHINE LEARNING TO ESTIMATE QUERY RESOURCE CONSUMPTION IN MPPDB
Document Type and Number:
WIPO Patent Application WO/2018/201948
Kind Code:
A1
Abstract:
Methods and apparatus are provided for using machine learning to estimate query resource consumption in a massively parallel processing database (MPPDB). In various embodiments, the machine learning may jointly perform query resource consumption estimation for a query and resource extreme events detection together, utilize an adaptive kernel that is configured to learn most optimal similarity relation metric for data from each system settings, and utilize multi-level stacking technology configured to leverage outputs of diverse base classifier models. Advantages and benefits of the disclosed embodiments include providing faster and more reliable system performance and avoiding resource issues such as out of memory (OOM) occurrences.
Inventors:
LIU LEI (US)
ZHANG MINGYI (US)
DONG YU (US)
LI HUAIZHI (US)
QIAO YANTAO (US)
ZHANG MINGYI (US)
DONG YU (US)
LI HUAIZHI (US)
QIAO YANTAO (US)
Application Number:
PCT/CN2018/084464
Publication Date:
November 08, 2018
Filing Date:
April 25, 2018
Export Citation:
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06F17/30; G06F9/445; G06N20/10
Foreign References:
| CN105279286A | 2016-01-27 | |||
| US20140372356A1 | 2014-12-18 | |||
| US20120246158A1 | 2012-09-27 |
Other References:
ABHAY MEHTA ET AL.: "Automated workload Management for enterprise Data Warehouses", IEEE DATA ENGINEERING BULLETIN, vol. 31, 1 March 2008 (2008-03-01)
See also references of EP 3607477A4
See also references of EP 3607477A4
Download PDF: