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

Unmanned aerial vehicle network transmitting power distribution method and device based on reinforcement learning

A technology of reinforcement learning and transmission power, which is applied in the field of UAV network transmission power distribution based on reinforcement learning, can solve the problems of wasting channel resources and low power distribution efficiency, and achieve the effect of improving system energy efficiency and realizing spectrum sharing

Active Publication Date: 2021-08-27
UNIV OF SCI & TECH BEIJING
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a UAV network transmission power allocation method and device based on reinforcement learning, to solve the problems of wasting channel resources and low power allocation efficiency in the resource allocation mechanism of the current UAV wireless ad hoc network. Artificial intelligence-based UAV wireless network resource allocation scheme

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
  • Unmanned aerial vehicle network transmitting power distribution method and device based on reinforcement learning
  • Unmanned aerial vehicle network transmitting power distribution method and device based on reinforcement learning
  • Unmanned aerial vehicle network transmitting power distribution method and device based on reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0068] Embodiments of the present invention provide a method for allocating transmission power of UAV network based on reinforcement learning, such as figure 1 As shown, the method includes the following steps:

[0069] S1. Initialize the state of the drone and the user, define the action space and the parameters of the neural network;

[0070] S2. Initialize the value function and the Q value of the current network state;

[0071] S3. Interact with the environment to receive reward feedback and calculate the Q value of taking the current action;

[0072] S4. Select the optimal action according to the maximum value of the reward obtained from the feedback;

[0073] S5. Update the next state of the system and store it in the experien...

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 an unmanned aerial vehicle network transmitting power distribution method and device based on reinforcement learning, and the method comprises the steps: initializing the states of an unmanned aerial vehicle and a user, and defining the parameters of an action space and a neural network; initializing a value function and a Q value of a current network state; interacting with the environment to receive reward feedback and calculating a Q value for adopting a current action; selecting an optimal action according to the maximum value of the reward obtained by feedback; updating the next state of the system and storing the next state into the experience pool; judging whether the experience number reaches an expected value or not, if so, starting deep reinforcement learning, and if not, continuing circulation; obtaining an instant reward according to a Bellman equation, carrying out deep learning by adopting a DPPO algorithm, and carrying out reinforcement learning by taking long-term reward function maximization as a target; and judging whether the value of the long-term reward function tends to converge, and terminating learning when the value tends to converge, thereby completing resource allocation optimization of the unmanned aerial vehicle wireless ad hoc network.

Description

technical field [0001] The present invention relates to the technical field of wireless communication networks based on drones, and in particular to a method and device for allocating transmission power of drone networks based on reinforcement learning in a wireless ad hoc network scenario for multiple drones. Background technique [0002] Unmanned Aerial Vehicle (UAV) has become an important partner in the field of wireless communication technology to provide effective wireless connection services due to its flexible controllability, high mobility, and good air-to-ground line-of-sight links. , Massive and other communication scenarios provide efficient solutions. UAV can be used as a mobile aerial base station to provide high-quality communication for users on the ground and improve the capacity of wireless networks. Compared with traditional ground communication systems, flexibility and low time cost are the advantages of UAV systems. With the help of UAV, a LOS communic...

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): H04W52/24H04W52/38G06N3/08G06F17/11H04W84/06
CPCH04W52/241H04W52/38G06N3/08G06F17/11H04W84/06Y04S10/50
Inventor 张海君李亚博唐书和唐睿卿隆克平高鹏李福昌
Owner UNIV OF SCI & TECH BEIJING
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