Channel access method of multi-priority wireless terminal based on deep reinforcement learning

A channel access method and reinforcement learning technology, applied in the channel access field of multi-priority wireless terminals, to achieve the effect of improving throughput and reducing scheduling delay

Pending Publication Date: 2021-11-05
NORTHWEST A & F UNIV
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] Aiming at the problems existing in the existing multiple access protocols, the present invention provides a channel access method for multi-priority wireless terminals based on deep reinforcement learning, especially relates to a channel access method for multi-priority wireless terminals based on deep reinforcement learning access method

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
  • Channel access method of multi-priority wireless terminal based on deep reinforcement learning
  • Channel access method of multi-priority wireless terminal based on deep reinforcement learning
  • Channel access method of multi-priority wireless terminal based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0117] Example 1: In a transmission network with two priority services, the network scene includes a base station, a DRL-MAC node, and a TDMA node; the DRL-MAC node is always in a state of service to be transmitted (saturated service scene).

[0118] Figure 6(a) shows the throughput results when the DRL-MAC node and a TDMA node coexist in a saturated business scenario, and its goal is to achieve the optimal throughput of the system.

[0119] Through Fig. 6 (a) can see that when the frame length is 10, the throughput result when the time slot N occupied by TDMA changes from 2 to 9. The slash-filled part and the solid-color filled part in the histogram indicate the throughput of the DRL-MAC node and the TDMA node, respectively. The circular marked dotted line is the total throughput simulated under the coexistence of DRL-MAC nodes and TDMA nodes, that is, the total throughput of the system. The diamond-marked dashed line represents the value of the theoretically optimal system ...

example 2

[0122] Example 2: In a transmission network with two priority services, the network scenario includes a base station, a DRL-MAC node, and a q-ALOHA node; the DRL-MAC node is always in the state of having services to transmit (saturated service scenario ).

[0123] Figure 6(c) shows the throughput results when the DRL-MAC node and a q-ALOHA node coexist in a saturated business scenario, and its goal is to achieve the optimal throughput of the system.

[0124]Figure 6(c) shows the throughput results of q-ALOHA when the access probability q varies from 0.2 to 0.9 when q-ALOHA nodes coexist with DRL-MAC nodes in a saturated traffic scenario. Figure 6(c) shows the throughput of the DRL-MAC node and the q-ALOHA node in the slash-filled part and the solid-color filled part, respectively. The circular marked dotted line is the total throughput of the simulation under the coexistence of DRL-MAC nodes and q-ALOHA nodes, which means the total throughput of the system. The diamond-marke...

example 3

[0129] Example 3: In a transmission network with two priority services, the network scene includes a base station, a DRL-MAC node, and a TDMA node; the DRL-MAC is in an unsaturated service scene.

[0130] The so-called unsaturated business scenario means that one data packet arrives in each time slot, and the arrival rate of data packets with different priorities is different. In this paper, the arrival probability of high-priority data packets is defined as 0.3, and the arrival probability of low-priority data packets is 0.7, after the data packets of different priorities arrive, they enter the data packet queues corresponding to different priorities and wait in line. The data packets of a certain amount of corresponding priority are entered into the queue respectively (in the present invention, the high and low priority queues are respectively initialized to enter 5 data packets in the queue), so as to avoid the situation that the access service queue is empty when the traini...

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 belongs to the technical field of wireless communication, and discloses a channel access method of a multi-priority wireless terminal based on deep reinforcement learning, and the channel access method of the multi-priority wireless terminal based on deep reinforcement learning comprises the following steps: establishing a network scene with different priority services; designing and defining a system model of a protocol, performing state space modeling and action space modeling according to a protocol network scene, and designing reward functions for different scenes; defining and establishing a neural network model used by the protocol, and training the network model through an experience tuple; and performing performance verification on the trained model through multi-scene simulation comparison. The channel access method of the multi-priority service wireless terminal is designed by using deep reinforcement learning, the method is more suitable for wireless networks with services of different priorities, the throughput of the system and the utilization rate of wireless channel resources are improved, and while the scheduling delay of high-priority services is shortened, the opportunity of the low-priority service to access the channel is improved.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and in particular relates to a channel access method for multi-priority wireless terminals based on deep reinforcement learning. Background technique [0002] At present, with the rapid development of wireless communication technology, emerging services such as data transmission and switching have increasingly strong demands on wireless channels. In a wireless network, when multiple users compete for the right to use a specific resource (such as the right to use a shared channel), the user sends a data packet by obtaining the right to use the channel. At this time, information from different users needs to occupy the channel For transmission, it may cause data packet collision, resulting in communication failure. In order to improve communication efficiency, it is necessary to introduce a multiple access protocol to determine the user's right to use resources and solve the problem...

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): H04W74/04G06F30/27G06N3/08
CPCH04W74/04G06F30/27G06N3/08
Inventor 孙红光高银洁张宏鸣李书琴徐超高振宇
Owner NORTHWEST A & F 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