Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Hybrid network measurement method and device based on SketchLearn, and medium

A hybrid network and measurement method technology, applied in the field of network measurement, can solve problems such as increased error and large memory of SketchLearn structure

Active Publication Date: 2020-10-27
NAT UNIV OF DEFENSE TECH
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention: Aiming at the above-mentioned problems of the prior art, a hybrid network measurement method, device and medium based on SketchLearn are provided. The disadvantage of excessive structural memory saves a lot of memory while maintaining and improving network measurement accuracy, and can improve the problem of increased error caused by statistically reduced samples caused by reducing the memory of the data plane

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
  • Hybrid network measurement method and device based on SketchLearn, and medium
  • Hybrid network measurement method and device based on SketchLearn, and medium
  • Hybrid network measurement method and device based on SketchLearn, and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Such as figure 1 As shown, the hybrid network measurement method based on SketchLearn in this embodiment includes:

[0046] 1) Receive data packets, count n stages of received data packets through a Hashpipe structure containing m stages, each stage contains n counting blocks, and flow out after completing n stages of counting, that is figure 1 The top-k part in , which is used to extract the top k large flows of the traffic algorithm, can be used to detect malicious traffic attacks, provide heavy hitter detection, etc., small in size and easy to operate, but cannot obtain the basic characteristics of all traffic ; Count the outbound data packets of the Hashpipe structure through the Sketch structure using the SketchLearn algorithm logic, that is figure 1 The sketch part in;

[0047] 2) Obtain the measurement result according to the count value in the Hashpipe structure and the sketch structure.

[0048] The hybrid network measurement method based on SketchLearn in t...

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 hybrid network measurement method and device based on SketchLearn, and a medium. The method provided by the invention comprises the following steps: receiving a data packet,counting n stages through a Hashpipe structure comprising m stages and each stage comprising n counting blocks, and flowing out after counting of n stages is completed; counting the data packets flowing out of the Hashpipe structure by adopting a SketchLearn algorithm logic through a sketch structure; and obtaining a measurement result according to counting values in the Hashpipe structure and thesketch structure. According to the method, the defect that the memory of the SketchLearn structure is too large due to the fact that the proportion of the large flow in the total flow is too large iseffectively overcome; and a large amount of memory is saved while the network measurement precision is maintained and improved, and the problem of error increase caused by statistical sample reduction due to reduction of the memory of a data plane can be solved.

Description

technical field [0001] The invention relates to network measurement technology, in particular to a SketchLearn-based mixed network measurement method, device and medium. Background technique [0002] Network measurements play an important role in data center networking, especially hard hitter detection, traffic frequency estimation, entropy, etc. These data are important network status parameters. With the rapid development of network bandwidth, accurate measurement methods (due to high memory and bandwidth utilization) are not suitable for deployment in high-speed networks. Sketch (sketch) structure was proposed and widely used. Sketch is a hash-based data structure. By setting a hash function, key-value data with the same hash value are stored in the same bucket to reduce space overhead. The data value in the bucket is used as a measurement result and is an approximation of the true value. Use technologies such as opening up two-dimensional address space and multiple h...

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): H04L12/26G06F16/901
CPCH04L43/14H04L43/50G06F16/9014
Inventor 文梅赵宵磊汤珉琎张春元
Owner NAT UNIV OF DEFENSE TECH
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
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