Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A prediction method of abnormal operation in cloud cluster environment

A prediction method and group environment technology, applied in the field of network information security, can solve problems such as the lack of effective methods

Active Publication Date: 2019-01-25
CIVIL AVIATION UNIV OF CHINA
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is still no effective method

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A prediction method of abnormal operation in cloud cluster environment
  • A prediction method of abnormal operation in cloud cluster environment
  • A prediction method of abnormal operation in cloud cluster environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The abnormal operation prediction method under the cloud cluster environment provided by the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0052] like image 3 As shown, the abnormal operation prediction method under the cloud cluster environment provided by the present invention comprises the following steps carried out in order:

[0053] 1) obtain task set from original task set; Original task set among the present invention selects the task data set of the first 10 days in the cluster task performance data set released by Google. The task data set contains 18623 jobs. The present invention randomly selects 18,000 jobs. These jobs include 6.5 million tasks. Each job includes one or more tasks, and all tasks form a task set.

[0054] 2) Extract the static features of the task from the above task set; in the task set with a total amount of N tasks, for the task to be processed, extract the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A prediction method of abnormal operation in cloud cluster environment, includes obtaining a set of tasks from the original set of tasks; extracting static features from the task set; dividing the tasks into normal tasks and abnormal tasks by support vector machine, calculating the dynamic characteristics of normal tasks and forming a dynamic characteristic sequence; using the improved unit gatedrecurrent neural network to process the dynamic feature sequences of multiple instant simultaneously on-line, retrieving the ID of the exception task, stopping the operation of the exception task if the identical ID is retrieved, and marking the job to which the exception task belongs as an exception job. The abnormal operation prediction method under the cloud cluster environment provided by theinvention is obviously superior to other methods in terms of accuracy and prediction time, so that the abnormal operation energy consumption can be effectively controlled.

Description

technical field [0001] The invention belongs to the technical field of network information security, in particular to a method for predicting abnormal operations in a cloud cluster environment. Background technique [0002] In recent years, cloud computing has become an important part of the informatization of modern society. It can not only provide very efficient and advanced tools for science, industry and commerce, but also provide a platform for ordinary users to process data on a daily basis. User-uploaded data and tasks are managed, scheduled, and processed by the cloud provider in an almost fully automated manner. [0003] In the computing process in the cloud cluster environment, a large number of jobs are processed and run at the same time. How to ensure the fast and efficient operation of massive jobs in the cloud computing system is very necessary. At the same time, how to ensure the processing speed of the cloud computing system The tasks are reliable, not afrai...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F11/30G06K9/62G06N3/04
CPCG06F11/3006G06F11/3065G06N3/045G06F18/2411Y02D10/00
Inventor 谢丽霞汪子荧杨宏宇
Owner CIVIL AVIATION UNIV OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products