Unlock instant, AI-driven research and patent intelligence for your innovation.

A data scheduling method and system

A data scheduling and data technology, applied in transmission systems, electrical components, etc., can solve problems such as server load imbalance, inability to guarantee scheduling, and inability to provide guarantee for data scheduling and timely processing, and achieve the effect of improving accuracy and timeliness

Active Publication Date: 2020-01-07
CHINA MOBILE COMM GRP CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Weighted Response, this method assumes that the server heartbeat detection is based on the speed of the machine, but this assumption may not always be true
Source IP Hash (Source IP Hash), for the same host, its corresponding server is always the same, using this method may lead to server load imbalance
[0004] It can be seen that the various scheduling methods provided in the above-mentioned prior art cannot guarantee the performance analysis and scheduling according to the attributes of the server, thus cannot provide guarantee for the timely processing of data scheduling

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 data scheduling method and system
  • A data scheduling method and system
  • A data scheduling method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] This embodiment provides a data scheduling method, such as figure 1 As shown, the method includes:

[0024] Step 101: Based on the historical processing performance data of at least one server, determine at least one attribute included in the historical processing performance data, and at least one category corresponding to each attribute;

[0025] Step 102: Establish a server evaluation model based on the historical processing performance data of the at least one server; wherein, the server evaluation model includes: at least one branch path composed of at least one attribute and at least one category, and a branch path composed of evaluation results The leaf nodes of each branch path of ;

[0026] Step 103: Based on the server evaluation model, evaluate at least one server in the server cluster to obtain an evaluation result for each server in the at least one server;

[0027] Step 104: Perform data scheduling according to the evaluation result of each server in the...

Embodiment 2

[0064] The specific implementation steps of the ID3 decision tree algorithm are as follows: figure 2 Shown:

[0065] First, initialize the parameters to obtain the data set D, attribute set A, category cj, and create a decision tree T;

[0066] Determine whether there is only one category cj in the current data set D, if so, directly add cj to the leaf node of T as a decision node;

[0067] If not, whether the attribute set A is empty, if it is empty, use the cj with the highest proportion in the data set D as the leaf node;

[0068] If it is not empty, calculate the entropy of the data set D, and calculate the entropy of each attribute;

[0069] Select an attribute with the largest information gain as the best classification attribute Ag;

[0070] Judging whether the information gain of the best classification attribute Ag is less than the threshold value, if less, then use the cj with the highest proportion in the data set D as the leaf node;

[0071] If it is not less ...

Embodiment 3

[0076] This embodiment provides a data scheduling system, such as image 3 shown, including:

[0077] A data preprocessing unit 31, configured to determine at least one attribute included in the historical processing performance data and at least one category corresponding to each attribute based on the historical processing performance data of at least one server;

[0078] A model building unit 32, configured to build a server evaluation model based on the historical processing performance data of the at least one server; wherein, the server evaluation model includes: at least one branch path composed of at least one attribute and at least one category, and The leaf nodes of each branch path formed by the evaluation results;

[0079] The server evaluation unit 33 is configured to evaluate at least one server in the server cluster based on the server evaluation model to obtain an evaluation result for each server in the at least one server;

[0080] The scheduling unit 34 is...

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

The invention discloses a data scheduling method and system. The method includes: based on historical processing performance data of at least one server, determining at least one attribute included in the historical processing performance data and at least one category corresponding to each attribute; establishing a server evaluation model based on the historical processing performance data of the at least one server, wherein the server evaluation model comprises at least one branch path formed by at least one attribute and at least one category and leaf nodes of each branch path formed by evaluation results; based on the server evaluation model, evaluating the at least one server in a server cluster to obtain the evaluation result of each server in the at least one server; and performing data scheduling according to the evaluation result of each server in the at least one server.

Description

technical field [0001] The invention relates to server cluster management technology in the communication field, in particular to a data scheduling method and system. Background technique [0002] As we enter the era of big data, the development of big data has become a national strategy. With the continuous development of hardware level, the performance of software and hardware facilities in data centers is constantly improving. Among them, the bottleneck of network bandwidth has been continuously broken through. At present, 10 Gigabit network has become the standard configuration of data centers. The storage and computing capabilities of servers are also continuously upgraded and optimized following Moore's Law. However, most traditional data distribution scheduling strategies can no longer meet the requirements of large data volume and real-time data transmission in the current big data environment. [0003] These scheduling strategies solve the connection and schedulin...

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 Patents(China)
IPC IPC(8): H04L29/08
CPCH04L67/1008H04L67/101H04L67/1029
Inventor 张宝海鲍媛媛
Owner CHINA MOBILE COMM GRP CO LTD