Transmission method based on learning energy-efficiency model

A transmission method and learning technology, applied in the field of end-to-end reliable Internet transmission, it can solve problems such as lower bandwidth utilization than UDT, inability to accurately control and measure network status, etc., to achieve high bandwidth occupancy and reduce end-to-end delay.

Active Publication Date: 2016-11-23
SICHUAN UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The Verus protocol does not accurately detect the network state, but establishes a short-term model for the delay and window relationship to adjust the window. This method can

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
  • Transmission method based on learning energy-efficiency model
  • Transmission method based on learning energy-efficiency model
  • Transmission method based on learning energy-efficiency model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. A transmission method based on a learning energy efficiency model provided by the present invention includes the following steps:

[0035] Step 1: Receive ACK packets and record the round-trip delay vectors of all ACK packets received and send window size vector i represents the current time period, using the formula For the round trip delay vector Perform weighted smoothing, i-1 represents the previous time period, α is the weighted smoothing factor, D g,i is the round-trip delay value smoothed by the maximum delay value in the i-th period; this step is to track the historical change trend of the network and reduce the impact of random events on congestion control;

[0036] Step 2: In order to judge the changing trend of the congestion control window, according to the formula Solve the normalized delay change rate G i , wher...

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 transmission method based on a learning energy-efficiency model. The method comprises the following steps: firstly, periodically recording historical change trends of a network, carrying out weighted smoothing on round-trip delays, and judging change trends of a congestion control window; then establishing models for a network energy efficiency and the congestion control window, when a new ACK (Acknowledgement) is received, updating the energy-efficiency and window models; finally combining with the change trends of the congestion window and the energy efficiency, predicting the size of the congestion control window in a next time period; for a network packet loss or timeout event, using the traditional TCP (Transmission Control Protocol) data packet retransmission mechanism, and when the packet loss is over, reusing the energy-efficiency model for processing. The transmission method disclosed by the invention lowers influences of network random events and estimation errors of the traditional algorithm, and can weigh the delays and particular emphasis of throughputs; in a high-speed network, the higher occupancy rate of a link bandwidth and lower end-to-end delays can be approximated, and the end-to-end delays performed on packet transmission are lowered.

Description

technical field [0001] The invention relates to the field of Internet end-to-end reliable transmission, in particular to a transmission method based on a learning energy efficiency model oriented to high-bandwidth and long-delay networks. Background technique [0002] With the continuous development of computer networks, the improvement of users' requirements for service quality and the continuous popularization of broadband network access, more and more high-bandwidth links will be applied to the Internet. The rapid increase of network bandwidth, satellites with high delay and the increase of multi-hop wireless links have caused some backbone networks in the Internet to have both high bandwidth and high delay characteristics, forming a high bandwidth delay product (High Bandwidth Delay Product, HBDP )network. In the case of increased single-flow bandwidth-delay product, the effectiveness of the congestion control mechanism for network transmission must be maintained. Trad...

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): H04L1/16H04L47/27
CPCH04L1/1607H04L41/145H04L43/0864H04L43/0888H04L47/27
Inventor 王俊峰李晓慧丁雪峰高展
Owner SICHUAN 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