Prediction-based network traffic load balancing method

A load balancing and network service technology, applied in data exchange networks, digital transmission systems, electrical components, etc., to solve problems such as flow damage

Inactive Publication Date: 2018-10-09
哈尔滨英赛克信息技术有限公司
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can achieve less session destruction rate by destroying the maximum flow, but there is still flow destruction

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
  • Prediction-based network traffic load balancing method
  • Prediction-based network traffic load balancing method
  • Prediction-based network traffic load balancing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] In order to better understand the above-mentioned technical solution, the above-mentioned technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0021] Such as Figure 1-Figure 3 As shown, a prediction-based network traffic load balancing method described in this embodiment includes the following steps:

[0022] S1. After the data packet arrives, extract the quadruple information of the data part, calculate the hash value through the hash function according to the quadruple information, and search the flow table according to the calculated hash value;

[0023] S2. Find the flow table node and directly enter step S4;

[0024] S3. No flow table node is found, enter the dynamic hash distribution module, find the destination host according to the dynamic hash distribution result, and create a flow table node;

[0025] S4. According to the back-end processing node information in the flow tab...

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 prediction-based network traffic load balancing method which comprises the steps of (S1) calculating a hash value by using a hash function according to quaternion informationand searching a flow table according to the calculated hash value, (S2) directly going to step S4 if a flow table node is found, (S3) entering into a dynamic hash distribution module if the flow tablenode is not found, finding a destination host according to a dynamic hash distribution result and creating a flow table node, (S4) constructing a data packet according to back end processing node information in the flow table and placing the data packet into a corresponding cache queue, (S5) allowing a sending thread to take data from the queue and send the data, (S6) collecting back end feedbackinformation with T as a period, (S7) calculating a predicted load value, and (S8) dynamically adjusting the proportion of virtual nodes in hash to achieve the effect of dynamic adjustment. A zero session destruction rate is achieved on the basis of ensuring load balance and a low packet loss rate.

Description

technical field [0001] The invention relates to the technical field of load balancing, in particular to a forecast-based network service flow load balancing method. Background technique [0002] Most current network session load balancing methods use a combination of static and dynamic methods to distribute traffic. First, use the flow table and hash distribution method to divide the traffic into different streams, and each stream corresponds to a processing node machine. By periodically collecting feedback information, when it is found that the load is uneven or a node is overloaded, the stream is remapped or the stream is redistributed according to other characteristics of the stream. [0003] Li Yanjun et al. proposed a load balancing method to adjust the maximum flow in the design and implementation of the multi-core platform intrusion detection system load balancing algorithm. This method first divides the flow into different flow streams through the hash method, and e...

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): H04L12/803H04L12/823H04L12/851H04L47/32
CPCH04L47/125H04L47/2483H04L47/32
Inventor 王志刚
Owner 哈尔滨英赛克信息技术有限公司
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