Wireless network distributed autonomous resource allocation method based on stateless Q learning

A wireless network and resource allocation technology, applied in the field of wireless network distributed autonomous resource allocation based on stateless Q-learning, can solve the problems of reducing network performance and difficult to obtain effectively, and achieve the best throughput effect

Active Publication Date: 2018-06-01
BEIJING UNIV OF TECH
View PDF3 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, some WiFi network channel allocation and transmission power control methods have been proposed, but each AP needs to know prior information such as the channel usage of other AP nodes in the network when optimizing the calculation.
In dense deployment scenarios, it is difficult to effectively obtain this information, thus reducing network performance

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
  • Wireless network distributed autonomous resource allocation method based on stateless Q learning
  • Wireless network distributed autonomous resource allocation method based on stateless Q learning
  • Wireless network distributed autonomous resource allocation method based on stateless Q learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] A distributed autonomous resource allocation method for a wireless network based on stateless Q-learning, comprising the following implementation steps:

[0042] Step (1): Set initial time t=0, Q value function Q(a k )=0, each node k is allocated 2 and 0 (dBm) respectively, and the number of channels and transmission power constitute the action set {a k}. Set the initial value of ε to 0.8.

[0043] Step (2): update time, t=t+1=1.

[0044] Step (3): At the iteration time t=1, randomly generate a number m=0.3, choose an action according to the ε greedy mechanism, and compare the two, because m<ε, the wireless node i randomly selects the new transmission power and the number of channels respectively 5(dBm) and 2. Conversely, if m is greater than ε, the action corresponding to the largest Q value among the obtained Q values ​​(that is, the transmit power and the number of channels) is selected.

[0045] Step (4): Calculate the maximum theoretical throughput of node i a...

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 wireless network distributed autonomous resource allocation method based on stateless Q learning. First, the number of channels and the transmitted power are taken as a set of actions, and a set of actions is randomly selected to calculate the actual network throughput; then the ratio of the actual network throughput and the theoretical throughput is taken as a reward after the action selection, and an action value function is updated according to the reward; and finally, the iterative adjustment of the actions can find the maximum solution of a cumulative reward value function, and the corresponding action thereof can reach the optimum performance of the wireless network. The method provided by the invention allows each node to autonomously perform channel allocation and transmitted power control to maximize the network throughput under the condition that prior information such as resource configuration of other nodes in the network is unknown.

Description

technical field [0001] The invention belongs to the field of wireless communication networks, and in particular relates to a wireless network distributed autonomous resource allocation method based on stateless Q learning. Background technique [0002] With the rapid increase of WiFi wireless network users and the rapid growth of the number and types of wireless devices, wireless services have higher and higher requirements for access quality. In order to improve the overall performance of the WiFi network, improve the service quality of the network and the actual user experience, it is necessary to effectively increase the transmission rate of the WiFi link and the area throughput. However, due to the same / different frequency interference in a dense networking environment, the network performance in the actual networking environment is not high. Therefore, how to improve the wireless network capacity in a complex environment is a difficult problem to be solved. [0003] T...

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): H04W72/04
CPCH04W72/04H04W72/0473Y02D30/70
Inventor 黎海涛吴晓媛罗佳伟
Owner BEIJING UNIV OF TECH
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