Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A d2d user resource allocation method based on deep reinforcement learning ddpg algorithm

A technology of reinforcement learning and user resources, applied in resources, computing, data processing applications, etc., can solve problems affecting user performance, user interference, etc.

Active Publication Date: 2020-07-10
HUAZHONG UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the existing technology, the purpose of the present invention is to solve the technical problem that in the prior art, when the D2D users share the channel of the cellular user, it will cause interference to the users who have already accessed and affect the performance of the users.

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 d2d user resource allocation method based on deep reinforcement learning ddpg algorithm
  • A d2d user resource allocation method based on deep reinforcement learning ddpg algorithm
  • A d2d user resource allocation method based on deep reinforcement learning ddpg algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0063] The object of the present invention is to maximize the information rate of D2D users and improve spectrum utilization without affecting the service quality of cellular users by jointly optimizing the transmission power and channel allocation strategy of D2D users. Using the deep learning method to apply the AC-based DDPG algorithm framework to the system model, the optimal D2D user power control and channel allocation strategy can be obtained, that is, in the cellular network, a set of optimal D2D user pairs can be obtained. Optimal transmit power and shared channel information make it po...

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 present invention discloses a D2D user resource allocation method based on the deep reinforcement learning DDPG algorithm. The present invention uses relevant information of cellular users and D2D users to obtain the optimal D2D user channel allocation and transmission power joint optimization strategy by using the deep reinforcement learning method , D2D users reduce the interference to cellular users by selecting appropriate transmit power and channel allocation, and at the same time maximize their own information rate, realize efficient resource allocation without affecting the QoS of cellular users, and improve the throughput of cellular networks The amount meets the requirements of green communication. The DDPG algorithm effectively solves the joint optimization problem of D2D user channel allocation and power control. It not only performs stably in the optimization of a series of continuous action spaces, but also requires far fewer time steps to obtain the optimal solution than DQN. Compared with the DRL method of the function, the deep policy gradient method based on the AC framework is more efficient in optimizing the strategy and faster in solving speed.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and more specifically, relates to a D2D user resource allocation method based on a deep reinforcement learning DDPG algorithm. Background technique [0002] With the increasing local wireless communication services, the pressure on the cellular network is increasing. As one of the key technologies of 5G communication, D2D (Device-to-Device) technology allows adjacent terminals to directly share data with each other under the control of the base station, forming a data sharing network and sharing the channel resources of the cellular network. To achieve the purpose of reducing the burden on the base station, improving spectrum utilization, and improving system throughput. [0003] D2D communication is a new technology that allows terminals to communicate directly through shared cell resources. It can increase the spectrum utilization efficiency of the cellular system, reduce the lo...

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): H04W52/24H04W52/26H04W52/38H04W72/04H04W72/08G06Q50/30G06Q10/06
Inventor 李强张雪艳楼瀚琼葛晓虎肖泳黄晓庆
Owner HUAZHONG UNIV OF SCI & TECH
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
Eureka Blog
Learn More
PatSnap group products