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

A Screen Update Transmission Method Based on Reinforcement Learning and Fountain Code

A technology of reinforcement learning and transmission method, which is applied in the field of cloud computing, can solve the problems of inability to achieve transmission efficiency, reduce the transmission window, etc., and achieve the effect of enhancing adaptability and reliable transmission

Active Publication Date: 2021-04-06
SICHUAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

RL-TCP introduces another effective reinforcement learning method SARSA into TCP NewReno, but TCPNewReno itself multiplies the sending window when packet loss occurs, making this method unable to achieve ideal transmission efficiency in a high packet loss rate transmission 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
  • A Screen Update Transmission Method Based on Reinforcement Learning and Fountain Code
  • A Screen Update Transmission Method Based on Reinforcement Learning and Fountain Code
  • A Screen Update Transmission Method Based on Reinforcement Learning and Fountain Code

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0049] Such as figure 1 As shown, the method of the present invention includes a transmission rate control module based on reinforcement learning and a forward error correction module based on fountain codes, and the specific process is as follows:

[0050] Step 1: On the sending side, the screen update data to be transmitted is segmented and sent to the sending rate control module based on reinforcement learning. This module preserves TCP NewReno's slow-start mechanism to quickly utilize bandwidth after screen update transmission starts or times out. When entering the congestion avoidance stage, the module enables the reinforcement learning method SARSA to learn the optimal sending strategy corresponding to different network states in real time. The network state consists of five parts: the exponentially weighted moving average of ...

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 screen update transmission method based on reinforcement learning and fountain codes. The reinforcement learning algorithm SARSA is used to control the transmission rate of screen updates, and the transmission behavior decision is made with a specified transmission target instead of a fixed rule, which improves the transmission method for different Adaptability to network conditions; use the Gilbert-Elliot model to model network packet loss behavior, use the system Raptor code and ARQ mechanism to ensure reliable transmission of screen updates, and reduce unnecessary duplication by dynamically setting the size of encoding blocks and the number of redundant packets The number of transmissions takes into account the real-time transmission. The method of the invention realizes efficient transmission of screen updates in the desktop as a service mode, and can better meet user requirements for quality of experience.

Description

technical field [0001] The invention relates to an end-to-end reliable transmission method in the desktop-as-a-service mode in the field of cloud computing, in particular to a screen update transmission method based on reinforcement learning and fountain codes. Background technique [0002] With the continuous evolution of cloud computing and virtualization technologies, cloud services have penetrated into every aspect of daily life. As an important branch of cloud services, desktop as a service is an emerging and economical cloud service model dedicated to meeting users' needs for remote access to personal desktops. In this service mode, users expect that the remote virtual desktop can retain the full functionality of the local desktop and ensure a good user experience. When a user interacts with a remote virtual desktop, screen updates, as a visual carrier of the user's perceived execution results, play an important role in the quality of experience. Existing research ha...

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 Patents(China)
IPC IPC(8): H04L1/00H04L1/20H04L12/841
CPCH04L1/004H04L1/0056H04L1/0079H04L1/203H04L47/283
Inventor 王俊峰郑弘迪张建平李凡
Owner SICHUAN UNIV