Dynamic spectrum anti-jamming model in fading environment and enhanced learning anti-jamming algorithm

A technology of dynamic spectrum and reinforcement learning, applied in transmission monitoring, electrical components, wireless communication, etc., can solve the problems of not considering the multipath effect Doppler frequency shift, lack of thinking about the real-time variability of wireless channels, and slow convergence speed

Inactive Publication Date: 2019-04-05
ARMY ENG UNIV OF PLA
View PDF3 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Some researchers combined deep learning with Q learning, and proposed to use deep learning algorithm to optimize the Q value table in Q learning (references: X.Liu, Y.Xu, L.Jia, et al, "Anti-Jamming Communications Using Spectrum Waterfall: A Deep Reinforcement Learning Approach,"in IEEE Communications Letters,vol.22,no.5,pp.998-1001,May 2018.), to achieve dynamic spectrum anti-interference, and solve the problem that the state space in Q-learning cannot be too large Insufficient, the performance is very good, but the

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
  • Dynamic spectrum anti-jamming model in fading environment and enhanced learning anti-jamming algorithm
  • Dynamic spectrum anti-jamming model in fading environment and enhanced learning anti-jamming algorithm
  • Dynamic spectrum anti-jamming model in fading environment and enhanced learning anti-jamming algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0121] The first embodiment of the present invention is specifically described as follows. The system uses matlab software to simulate and verify the fading channel environment and the proposed algorithm, and at the same time analyzes the convergence of the proposed algorithm and evaluates its anti-interference performance. Additionally, to analyze the throughput performance of the system, it is compared with a perception-based random channel selection algorithm. The random algorithm based on perception randomly selects channels from idle channels, which is a relatively intuitive channel selection algorithm.

[0122] The wireless communication environment includes 1 channel of frequency-sweeping interference signal, 1 transmitter and 1 receiver, there are M=5 available channels, and N=4 channel transmission rates. The relevant parameters of the specific Markov channel model and the relevant parameter settings of reinforcement learning are shown in Table 1.

[0123] Table 1 Si...

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 dynamic spectrum anti-jamming model in a fading environment and an enhanced learning anti-jamming algorithm. The model comprises a transmitter, a receiver and a jammer duringthe dynamic spectrum anti-jamming process of a wireless communication system, wherein the jammer generates jamming signals to jam user communication; the transmitter and the receiver transmit data frames through a data link, and the control information is transmitted through a control link; and the receiver acquires the channel information through data communication and broadband spectrum sensing, and the enhanced learning algorithm is executed for optimizing a channel selection strategy. The algorithm is as follows: a user transmits data on a data channel and obtains the current channel transmission rate, and the return value of the current working channel is calculated; the jamming channel at the current time is obtained through spectrum sensing; a new transmission channel is decided through enhanced learning, a Q value table is updated, and due to such cycle, the state of the optimal strategy can be obtained. The dynamic spectrum anti-jamming problem in the fading environment can be solved, and the throughput of the system is improved.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, in particular to a dynamic spectrum anti-jamming model in a fading environment and a reinforcement learning anti-jamming algorithm. Background technique [0002] Due to the rapid growth of demand for wireless communication services, spectrum resources are increasingly scarce. In addition, with the continuous improvement of the intelligent level of interference, the wireless communication system is facing severe challenges. In order to ensure the reliable transmission of wireless communication in the new interference environment, how to achieve efficient communication anti-interference is becoming more and more urgent. [0003] Aiming at the problem of reasonable allocation of spectrum resources, scholars in the field of intelligent anti-jamming have carried out research on dynamic spectrum anti-jamming. Dynamic spectrum access (DSA) breaks through the current static and fixed freq...

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): H04B17/382H04B17/391H04W72/08
CPCH04B17/382H04B17/3911H04B17/3912H04W72/541
Inventor 徐煜华徐以涛程云鹏孔利君丁国如张玉立
Owner ARMY ENG UNIV OF PLA
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