Self-adaptive scheduling method of data service cluster

A scheduling method and data service technology, applied in digital data processing, program startup/switching, resource allocation, etc., can solve problems such as information islands and no available data for big data research

Pending Publication Date: 2020-06-30
北京大学(天津滨海)新一代信息技术研究院
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The current artificial intelligence is inseparable from data, but the collection of big data has become an obvious bottleneck, a large number of data barriers have emerged, and a large number of "information islands" have formed, making big data research face the dilemma of no available data
Due to the inherent closed nature of mobile applications on smart devices, the problem of "information islands" is even more serious

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
  • Self-adaptive scheduling method of data service cluster
  • Self-adaptive scheduling method of data service cluster
  • Self-adaptive scheduling method of data service cluster

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] Such as figure 1 As shown, the present invention provides an adaptive scheduling method for data service clusters, including:

[0053] API call request, the API call request is arranged after the existing request according to the first in first out (FIFO) order;

[0054] Read the top request, parse the request, and read the requested interface i′;

[0055] Traverse W j, i And C j, i Corresponding column, where W n×m To maintain the receiving window matrix, the element W j, i Record the maximum number of simultaneous calls of interface i on device j, C n×m Is the concurrent number matrix, element C j, i Record the current concurrency number of interface i on device j (the number of requests being processed); get the set of candidate devices (that is, the devices whose current concurrency number is less than the receiving window) set D'(D is the set of all devices) D'= {j|C j, i′ j, i′ ,J∈D}

[0056] When D′ is an empty set, rearrange the API call requests in the request ...

Embodiment 2

[0074] Single device service capability measurement

[0075] Step 1: Control variables

[0076] (1) The hardware and software configuration of the device: the measurement is performed on devices of the same manufacturer, the same model, and the same Android version. All applications that are allowed to be uninstalled will be uninstalled, and only the applications and interfaces to be measured will be installed. Connect the device to the power source and keep the battery fully charged.

[0077] (2) Network environment: Connect the device to a stable Wi-Fi access point and measure during off-peak hours.

[0078] Step 2: Measure F i (v)

[0079] At rate v=v 0 Send a request to call the interface i to the device to measure the completion rate w′ of the request; repeat the operation several times to obtain the mean value of w′ then Similarly, F can be measured i (v) The result when v takes other values. Since measuring a single F i The operation of (v) is time-consuming, and the value ra...

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 relates to the field of task scheduling, in particular to a self-adaptive scheduling method of a data service cluster. The method comprises the following steps: sending a calling request, analyzing the request, and reading a requested interface; screening candidate equipment meeting conditions; selecting candidate equipment with the lowest load; executing the request on the candidateequipment, if the set time is exceeded or the execution fails, recording the execution failure, judging a failure condition, and executing the next instruction; and if the execution succeeds, recording the execution success, judging a success condition, and executing the next instruction. According to the invention, the equipment with the minimum load is selected to realize flow average distribution, and the instantaneous request flow reaching the equipment does not need to be accurately monitored; and adjustment is realized automatically according to success or failure of interface calling so as to automatically adapt to an unknown interface.

Description

Technical field [0001] The invention relates to the field of data scheduling, in particular to an adaptive scheduling method of data service clusters. Background technique [0002] The current artificial intelligence is inseparable from data, but the collection of big data has become an obvious bottleneck. Data barriers have appeared in large numbers, and the formation of a large number of "information islands" makes big data research face the dilemma of no available data. The problem of "information islands" is even more serious due to the inherent closure of mobile applications. [0003] One way to solve the problem of “information islands” of smart devices is to develop a new software definition theory based on classic software definition theories, that is, to expose the controllable components of smart devices through application programming interfaces (API) to realize smart devices On-demand management and on-demand services. [0004] Different from the classic data service cl...

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
IPC IPC(8): G06F9/50G06F9/48G06F9/54
CPCG06F9/5005G06F9/4806G06F9/546Y02D10/00
Inventor 黄罡董瀚景翔蔡华谦姜海鸥
Owner 北京大学(天津滨海)新一代信息技术研究院
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap