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

Jumping Spectrum Sensing Method Based on Reinforcement Learning

A technology of spectrum sensing and reinforcement learning, applied in machine learning, transmission monitoring, instruments, etc., can solve the problems of reducing the transmission data time and affecting the transmission effectiveness, so as to reduce the sensing overhead, reduce the number of sensing times, and improve the efficiency of data transmission Effect

Active Publication Date: 2021-09-24
DALIAN UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Sensing before each time slot transmission can effectively control the interference of secondary users to primary users, but frequent spectrum sensing will reduce the time of data transmission, affect the effectiveness of transmission, and also bring huge energy consumption for perception overhead

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
  • Jumping Spectrum Sensing Method Based on Reinforcement Learning
  • Jumping Spectrum Sensing Method Based on Reinforcement Learning
  • Jumping Spectrum Sensing Method Based on Reinforcement Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The specific implementation of the present invention will be described in detail below in conjunction with specific examples, and the method of the present invention is not limited to the specific examples. Consider a time-slot system composed of a pair of cognitive radio transceivers. There are 4 channels for dynamic access, and the transmitter can select 2 channels for data transmission. Set the maximum number of skipped slots to 5. The concrete steps of the inventive method are as follows:

[0026] 1. Establish a Q table for all "state-action" pairs, initialize all values ​​in the Q table to 0, and set the initial state as 4 channels are all idle;

[0027] 2. Select 2 channels to access, and the selection method is as follows: select the action with the largest Q value among all actions in the state s corresponding to the Q table with probability 1-ε, that is, An action is randomly chosen with probability ε. This operation is performed twice, and when it is perfo...

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 provides a hopping spectrum sensing method based on reinforcement learning, which belongs to the field of wireless communication, and particularly relates to cognitive radio technology, and provides a low-cost, intelligent spectrum sensing method for dynamic spectrum access. Considering the continuous characteristics of the spectrum idle state, this method allows the device to skip part of the sensing time slot when accessing the channel. Compared with the traditional periodic sensing strategy, it can reduce the sensing overhead and improve the transmission efficiency. This method adopts a reinforcement learning algorithm, takes channel occupancy as the state, and channel selection and perceptual skip time slots as actions. By evaluating different actions in different states, the device can intelligently formulate optimal strategies. This method does not rely on a specific statistical model of the spectrum state, and the device can adaptively determine the optimal access and sensing strategy through the learning of the environment.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and relates to a hopping spectrum sensing method based on a reinforcement learning algorithm, in particular to cognitive radio and dynamic spectrum access. Background technique [0002] In recent years, with the rapid development of the Internet of Things, the amount of data that mobile wireless networks need to carry is increasing day by day, and spectrum has gradually become a scarce and important natural resource. Cognitive radio technology can use spectrum sensing and dynamic spectrum access to allow secondary users to access vacant frequency bands without affecting the use of spectrum owners (primary users), so as to effectively use vacant spectrum resources, improve spectrum utilization efficiency, and expand Network capacity is regarded as one of the important enabling technologies for mobile wireless networks in the future. [0003] Spectrum sensing is an important part of...

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): H04B17/382H04W72/04G06N20/00
CPCH04B17/382H04W72/0453G06N20/00H04W72/53
Inventor 李轩衡董一锋张雨浩孙弘毅张仁浩丁海川
Owner DALIAN UNIV OF TECH
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