Cognition anti-interference communication method based on reinforcement learning algorithm

A communication method and reinforcement learning technology, applied in wireless communication, transmission monitoring, network traffic/resource management, etc., can solve problems such as difficulty in learning effective anti-interference strategies, and achieve the effect of maximizing throughput

Active Publication Date: 2019-04-16
BEIJING UNIV OF TECH
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the proposed Q-learning anti-jamming technology, it is difficult to learn an e

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
  • Cognition anti-interference communication method based on reinforcement learning algorithm
  • Cognition anti-interference communication method based on reinforcement learning algorithm
  • Cognition anti-interference communication method based on reinforcement learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0030] Step (1): Set iterative time t=0, time range T=20000, according to the perceived non-interference channel {1,2} and power {4,8,12,16} to form different frequency channels and transmission power Combination subset {f u ,p v }, where f u ∈{1,2},f v ∈{4,8,12,16}, the index of each subset is marked as k∈{1,...,8}, and all subsets form a set {{1,4},...,{2,16 }};

[0031] Step (2): At the initial time t=0, for any node j, traverse all subsets, calculate the metric value of node j for each subset, and obtain the set of all subset metric values ​​corresponding to wireless network node j

[0032] As an example, calculate the metric value of the k=1th subset of node j=1 The specific steps are as follows:

[0033] Step (2.1), first calculate the signal-to-interference and noise ratio of the wireless network node j=1 to select the k=1th subset according to the selected channel and power Among them, node j=1 selects the received power of the k=1th subset as P j,k -249.4150dBm, ground n...

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 cognition anti-interference communication method based on a reinforcement learning algorithm. Firstly, spectrum sensing is utilized for obtaining an interference-free channeland power, subsets in which different frequency channels and transmitting power are combined are formed, an index value of each subset is marked, and all the subsets form a candidate resource set; then at an initial moment, each node traverses all the subsets, and a metric of the node for each subset is calculated, so that a set of the metrics of all the subsets corresponding to the node is obtained; then the node selects a subset corresponding to a maximum metric from a set of corresponding metrics, and the metric corresponding to the subset is updated; and finally performing iterative computation on the metric in a time range T, wherein the subset corresponding to the maximum metric can enable throughput of the node to be maximized. The cognition anti-interference communication method disclosed by the invention learns an optimal strategy by utilizing the reinforcement learning algorithm, and each node performs independent adjustment, channel selection and power distribution, so thatthroughput of an anti-interference communication system is maximized and the anti-interference aim is achieved.

Description

technical field [0001] The invention relates to the field of wireless communication, and relates to a communication anti-interference method for improving the capacity of a cognitive wireless network. Background technique [0002] At present, high-density, multi-band deployed wireless communication systems have brought serious electromagnetic interference. Therefore, while pursuing higher speed, longer distance and better service quality, the wireless communication system needs to greatly improve its anti-interference ability. [0003] Generally, spread spectrum anti-jamming and adaptive antenna technology are widely used in communication systems. Spread spectrum anti-interference is usually divided into direct sequence spread spectrum and frequency hopping. The anti-interference principle is to expand the signal spectrum in the frequency domain, thereby reducing the power density of the spectrum, so that useful signals are submerged in interference and environmental noise....

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): H04B17/309H04B17/336H04B17/382H04W28/02H04W28/20
CPCH04W28/0236H04W28/20H04B17/309H04B17/336H04B17/382
Inventor 黎海涛罗佳伟
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