Unlock instant, AI-driven research and patent intelligence for your innovation.

A Communication Anti-Jamming Method Based on Deep Deterministic Gradient Reinforcement Learning

A reinforcement learning and gradient technology, applied in the directions of interference to communication, neural learning methods, biological neural network models, etc., can solve the problems of quantization error, power selection results cannot be optimized, and overcome quantization errors and reduce network complexity. , the effect of improving performance

Inactive Publication Date: 2020-07-10
UNIV OF ELECTRONICS SCI & TECH OF CHINA +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method will introduce quantization error when quantizing and discretizing the power, so that the power selection result cannot be optimal.

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
  • A Communication Anti-Jamming Method Based on Deep Deterministic Gradient Reinforcement Learning
  • A Communication Anti-Jamming Method Based on Deep Deterministic Gradient Reinforcement Learning
  • A Communication Anti-Jamming Method Based on Deep Deterministic Gradient Reinforcement Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] figure 1 It is the specific implementation method of the algorithm of the present invention, combined below figure 1 Describe each step and its principle in detail.

[0037] The algorithm implementation framework of the method proposed by the present invention based on the depth-determined gradient strategy reinforcement learning continuous strategy selection anti-interference method is as follows: figure 1 shown. In step S1, S1.1 completes interference and wireless environment modeling. In the scenario, multiple interference sources interfere with legal communication links. The interference methods may include but are not limited to: single-tone interference, multi-tone interference, linear frequency sweep interference, partial frequency band interference, and noise frequency hopping interference. The interference source can realize the dynamic adjustment of interference to legitimate users by adjusting interference parameters or switching interference modes. The s...

Embodiment 2

[0083] The convolutional neural network structure proposed by the present invention for anti-interference decision-making is as follows: figure 2 As shown: In the simulation, it is assumed that the system is divided into 128 sub-channels, and a 128×128 spectrum time slot state matrix is ​​constructed according to the spectrum sampling signal as the input of the convolutional neural network; then three convolutional layers, two pooling layers and two The fully connected layer outputs a 1×128 power vector. Specifically, the convolutional layer, pooling layer and operations in the convolutional neural network are as follows:

[0084] Assuming that the input data of the convolution operation is I, the corresponding convolution kernel K has the same dimension as the input data. Take three-dimensional input data as an example (when the input data is two-dimensional, the third dimension can be regarded as 1). The convolution operation requires the third dimension of the convolutio...

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 belongs to the technical field of wireless communication, and relates to a communication anti-jamming method based on depth determination gradient reinforcement learning. The present invention first constructs the interference environment model according to the number of interference sources and the wireless channel model; constructs the utility function according to the legal user communication quality index, and takes the utility function as the reward in the learning; constructs the spectrum information sampled in different time slots into spectrum time slots matrix, which describes the state of the disturbance environment. Then, the gradient reinforcement learning mechanism is determined according to the depth, and the convolutional neural network is constructed. When making anti-interference decision-making, the environment state matrix realizes the anti-interference strategy selection of the corresponding state in the continuous space through the target actor convolutional neural network. The basis of the invention. The reinforcement learning mechanism that determines the gradient strategy in depth completes the continuous anti-jamming strategy selection in communication. It overcomes the quantization error caused by quantizing the discrete processing strategy space, reduces the number of neural network output cells and network complexity, and improves the performance of the anti-interference algorithm.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and relates to a communication anti-jamming method based on depth determination strategy gradient reinforcement learning. Background technique [0002] With the development of wireless communication technology, the electromagnetic environment faced by wireless communication systems is increasingly complex and harsh. It may suffer from unintentional interference from its own communication, and may also be affected by interference signals intentionally released by the enemy. The traditional anti-jamming means adopt fixed anti-jamming strategies for the static jamming mode of the jamming source. With the intelligentization of jamming methods, jamming sources can dynamically adjust jamming strategies according to changes in the communication status of legitimate users, making traditional anti-jamming methods unable to guarantee normal communication of legitimate users in a dynamic jamm...

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): H04K3/00G06N3/04G06N3/08
CPCH04K3/20H04K3/40G06N3/08G06N3/045
Inventor 黎伟王军李黎党泽王杨
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA