Unlock instant, AI-driven research and patent intelligence for your innovation.

Heterogeneous network multipath scheduling method and system based on artificial intelligence

A heterogeneous network and artificial intelligence technology, applied in transmission systems, digital transmission systems, data exchange networks, etc., can solve problems such as the inability to adapt to the MPTCP multi-subflow environment, and achieve the effect of improving aggregation performance and reducing application delay

Pending Publication Date: 2021-07-23
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, if all the properties of the TCP layer are taken into account, there will be no functional model that can accurately measure the value of GAP
Therefore, conventional modeling methods cannot adapt to the dynamically changing MPTCP multi-subflow environment

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
  • Heterogeneous network multipath scheduling method and system based on artificial intelligence
  • Heterogeneous network multipath scheduling method and system based on artificial intelligence
  • Heterogeneous network multipath scheduling method and system based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The invention designs an artificial intelligence-based multipath transmission control protocol (MPTCP) data packet scheduling optimization method and system. The system uses the Transformer network and deep enhanced neural network to summarize the historical experience of packet scheduling through exploration and utilization, so as to accurately and adaptively adjust the GAP value of each TCP subflow to minimize the multipath scheduler receiving end. Out of order situation. Mainly include the following:

[0045] Key point 1: A deep reinforcement learning multi-path packet scheduling framework is proposed, which implements the experience-driven MPTCP packet scheduling logic. It does not rely on an accurate and rigid linear mathematical model, fully considers the random properties of the TCP layer of each sub-flow, and uses a deep neural network as a function approximation for GAP adjustment according to the runtime state of a heterogeneous wireless network to achieve ac...

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 heterogeneous network multipath scheduling method and system based on artificial intelligence. The method comprises the following steps of: summarizing historical experience of data packet scheduling by exploring and utilizing a Transform network and a deep enhanced neural network so as to accurately and adaptively adjust a GAP value of each TCP substream to minimize the disorder condition of a receiving end of a multi-path scheduler.

Description

technical field [0001] The present invention relates to the field of computer network transmission control, in particular, the present invention relates to a scheduling method and system based on experience-driven heterogeneous network multipath transmission control protocol (MPTCP). Background technique [0002] Currently, the most widely used multipath solution is MPTCP, which enables unmodified applications to utilize multiple heterogeneous network interfaces such as cellular, WiFi, and Ethernet. MPTCP is already implemented in the linux kernel and is supported by many commercial products. MPTCP adds a shell layer between TCP and the application layer, and can establish multiple TCP subflows on each network interface. The multipath scheduler determines the number of packets distributed from the send queue to each TCP subflow. However, the heterogeneity of TCP subflows makes it challenging to design a good scheduler. A wrong scheduler can lead to severe out-of-order pac...

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): H04L12/707H04L12/729G06N3/08H04L45/24H04L45/125
CPCH04L45/125H04L45/24G06N3/08
Inventor 廖彬彬张广兴王德志赵挽涛李振宇谢高岗
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI