Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-user reinforcement learning-based cognitive wireless network anti-hostile interference method

A cognitive wireless network and reinforcement learning technology, which is applied in the field of cognitive wireless network anti-hostile interference based on multi-user reinforcement learning, can solve problems such as increasing the difficulty of anti-interference

Active Publication Date: 2015-10-21
XIAMEN UNIV
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] For the adaptive jammer, the adaptive jammer will only launch an attack when the transmission power of the transmitter successfully transmitting legal information is sufficient to be successfully received by the receiving node, which can be called the legal information transmission power at this time as the jamming gate Limit H J , so it increases the difficulty of cognitive user anti-interference

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
  • Multi-user reinforcement learning-based cognitive wireless network anti-hostile interference method
  • Multi-user reinforcement learning-based cognitive wireless network anti-hostile interference method
  • Multi-user reinforcement learning-based cognitive wireless network anti-hostile interference method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The following examples will further illustrate the present invention.

[0031] Embodiments of the present invention include the following steps:

[0032] 1) The cognitive source node initializes the learning factor α s , discount factor γ s , step size n, learning rate (δ l and δ w ), the current launch strategy π s (t s , u s )=1 / |A s |, Q s Table of values, V s The value table and the number of occurrences of state t C(t s ) value is 0;

[0033] 2) The cognitive source node perceives the state t when the step size n=1, according to the hybrid launch strategy Choose an action from state t conduct appropriate exploration;

[0034] 3) The cognitive source node first needs to detect the access state σ of the primary user every time. When the primary user accesses the target channel at the current moment, the cognitive source node selects the transmission power 0; otherwise, the state t is based on the hybrid transmission strategy π s (t s , u s ) from st...

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 relates to wireless network security, particularly to a multi-user reinforcement learning-based cognitive wireless network anti-hostile interference method. Cognitive source nodes adopt a multi-user reinforcement learning strategy to automatically select transmitted power by observation of status information of a master user working condition, self-adaptive jammer transmitted power and the like. Learning of multiple cognitive source nodes is performed at the same time, and each time transmission of a data packet is finished, according to obtained immediate returned report and a state of the next moment, an update state, a behavior and a mapping relation, and according to feedback information, the learning rate of the multi-user reinforcement learning algorithm is replaced, thereby improving the signal to interference ratio of a receiving end, and finally obtaining the optimal transmitted power. Each cognitive source node can assist forwarding of the data packet or transmit data by itself. The method utilizes a multi-user reinforcement learning mechanism, and through a method of attempting and comparison, improves communication efficiency of a cognitive wireless network in a scene of an intelligent hostile jammer.

Description

technical field [0001] The invention relates to wireless network security, in particular to a cognitive wireless network anti-hostile interference method based on multi-user reinforcement learning. Background technique [0002] The development of wireless communication is restricted by issues such as the shortage and utilization of spectrum resources, and the proposal of Cognitive Radio (CR) technology can effectively improve the utilization of spectrum. Due to the broadcast characteristics of wireless channels, cognitive radio networks are extremely vulnerable to hostile interference attacks, making wireless network security issues urgent to be resolved. [0003] The attack mode of the jammer is to prevent cognitive users from accessing the communication channel or destroy the normal transmission of information between nodes by intermittently or continuously transmitting jamming signals to the wireless channel. As a traditional anti-interference technology, spread spectrum...

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): H04W52/04H04W52/24
CPCH04W52/04H04W52/243
Inventor 肖亮周长华陈桂权刘金亮
Owner XIAMEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com