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

Distributed computing method based on hive mind

A distributed computing and thinking technology, applied in the direction of electrical components, transmission systems, etc., can solve problems such as failure to take automatic remedial measures for short boards, system throughput decline, etc., to reduce operation and maintenance intervention work, high throughput, and work The effect of maximizing efficiency

Active Publication Date: 2016-06-08
HYLANDA INFORMATION TECH
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Common parallel indexing frameworks in the industry, such as HADOOP, Groovy, and asynchronous queue technology often only solve the problem of data distribution to multiple processing nodes, but for streaming real-time data processing, the shortcomings in the barrel are not considered After the occurrence of automatic remedial measures, when the system has a short board in processing node capabilities, the throughput of the entire system will drop sharply. At this time, it can only be maintained and adjusted by manual intervention

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
  • Distributed computing method based on hive mind

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be described in detail below by means of the accompanying drawings and specific embodiments.

[0033] like figure 1 As shown, the distributed computing method based on hive thinking of the present invention comprises the following steps:

[0034] A. Roughly estimate the calculation logic of the indexing rules in the system, and quantify them numerically to obtain the complexity value;

[0035] B. According to the limit of the complexity of the rules that can be loaded by a single node, group all the rules so that the complexity of each group of rules is basically average and does not exceed the upper limit;

[0036] C. The cluster sets the unique information board Zookeeper, and publishes the rule grouping logic on it;

[0037] D. The cluster sets up the high-speed data exchange center Redis, and all data flows here to wait for indexing;

[0038] E. Put in several computing node workers, and the nodes will first automatically select their o...

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 provides a distributed computing method based on a hive mind. Computation logic is split into parallel working groups, corresponding computing resources are input to the groups for working, an information board and system state monitoring and reporting mechanism are established in a working process, thus each computing node can master the system state, and the computing node is entitled with intelligent selection rights, each node is independently assigned to work and attributes to the cluster together, the working efficiency of each node is maximized, namely no too busy node or too idle node exists, the cluster entirety automatically adjusts, automatically overcomes the system faults and automatically solves the system short boards, the system throughput is always maintained at a relatively high level, and the operation and maintenance intervention works are greatly reduced.

Description

technical field [0001] The invention relates to the technical field of parallel computing frameworks, in particular to a distributed computing method based on bee colony thinking that can automatically adjust computing node resources in a system. Background technique [0002] After the Internet data is collected, each piece of collected data needs to be indexed once, and the necessary labels are added to the data according to the customer's real-time data subscription requirements. This streaming real-time data indexing is a necessary part of data mining. Due to the huge amount of data collected and the many data indexing rules (calculation logic), stand-alone computing cannot meet the demand, and parallel computing is imperative. However, due to the continuous growth and changes of the business (customer's real-time data subscription requirements and types), the data indexing rules are also constantly increasing and updating, and the number of rules that can be accommodated...

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): H04L29/08
CPCH04L67/10
Inventor 常毅杨伟锋
Owner HYLANDA INFORMATION TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com