Online data flow QoS identification method and system based on service type

A technology of business type and identification method, applied in the direction of digital transmission system, transmission system, data exchange network, etc., can solve the problems of incompatibility, lack of model versatility, distinction of business types, etc., to achieve high accuracy and good universality and usability, the effect of improving accuracy

Inactive Publication Date: 2020-07-17
SHANGHAI JIAO TONG UNIV
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the data packets classified by this method are limited to IP packets and are not applicable to all protocols.
Another shortcoming is that the classification model of this method has been determined in the training stage, but the selected features such as IP addresses are changed in practice, and the relationship between different time and place and business type is not the same, resulting in The phenomenon of overfitting occurs, and the model has insufficient versatility among different networks
[0004] F. Mendoza et al. in the paper "SDN-based traffic engineering for improved resilience in integrated satellite-terrestrial backhaul networks" (2017 4th International Conference on Information and Communication Technologies for Disaster Management (ICT-DM), Münster, 2017, pp.1-8. ) has proposed an elastic resource allocation method based on different traffic bandwidths in a software-defined space-ground integrated network, but does not distinguish specific business types, so that it cannot ensure that the QoS requirements of each data flow are met
Another similar problem is that the classification model of this method has been determined at startup, and the model has insufficient generality among different networks.

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
  • Online data flow QoS identification method and system based on service type
  • Online data flow QoS identification method and system based on service type
  • Online data flow QoS identification method and system based on service type

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0124] Step 1: Read in historical data and build an initial model. Read in the marked historical flow information from the database, each piece of information is the information of a data flow, with 6 fields of source address, destination address, source port, destination port, protocol type and business type. The source address and destination address are in the form of IP addresses, which are regarded as a 32-bit binary number, which is converted into a decimal number and then normalized. The destination port and source port are also normalized, and a data stream is transformed is a 5-dimensional vector, and the data set X={x 1 ,x2...,x N}. There are five types of services: general services, delay-sensitive services (real-time calls, etc.), high-traffic services (video transmission, etc.), high-mobility services (automatic driving, etc.), and wide-coverage services (multi-purpose address broadcast services).

[0125] Use the K-means algorithm to cluster it for unsupervise...

Embodiment 2

[0137] The purpose of the present invention is to overcome the deficiencies in the prior art, and provide a method that can accurately identify the service quality requirements of the entire data flow through the information contained in some packets in the data flow in the software-defined space-ground integrated network . This method is based on online incremental learning and the QoS model of Tiandi Network, which can adaptively find out the service type of each data flow and its corresponding network environment requirements, and does not need to manually input the QoS information of each data flow. The manual adjustment of the parameters of the identification method not only improves the accuracy of the identification but also enhances the universality of the method, which can be used in satellite networks, software-defined networks, space-ground integrated networks and other fields.

[0138] The present invention is realized through the following technical solutions. The...

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 an online data flow QoS (Quality of Service) identification method based on a service type, which comprises the following steps: S1, classifying by using a part of historical flow with historical labels, carrying out offline model training, establishing an initial classification model, and installing the model in a controller in an SDN (Software Defined Network) to serve asan initial classifier; and S2, when the data flow reaches the switch, matching the data packet of the data flow with a forwarding flow table in the switch, if matching succeeds, performing operation according to an instruction designed in the forwarding flow table, and otherwise, packaging the data packet of the data flow and uploading the packaged data packet to a controller. The method providedby the invention can obtain very high accuracy, has self-adaptive adjustment capability, and can be used for space-ground networks at different time and different geographic positions.

Description

technical field [0001] The present invention relates to the field of satellite network, software-defined network, quality of service (QoS) model and incremental learning, in particular, to a method and system for identifying online data stream QoS based on service type. In particular, it relates to a service-sensitive online data flow QoS identification method in a space-ground integrated network. In particular, it relates to a method for identifying data streams used to ensure quality of service in a software-defined network (SDN) space-ground integrated satellite network. Background technique [0002] Traffic identification is the most critical technology in the application of traffic engineering in software-defined networks. The method and accuracy of its identification directly affect the performance of subsequent routing algorithms and the final quality of service and user experience provided. Therefore, accurate identification of data flows The QoS requirements can gr...

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): H04L12/851
CPCH04L47/2441H04L47/2483H04L47/24
Inventor 唐飞龙马启晨姚斌俞嘉地
Owner SHANGHAI JIAO TONG UNIV
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