Cache strategy method in D2D network based on deep reinforcement learning

A reinforcement learning and network caching technology, applied in neural learning methods, biological neural network models, electrical components, etc., can solve the problems of high energy consumption, long delay, and low hit rate of cache content placement, and achieve low energy consumption and delay. short time effect

Active Publication Date: 2019-04-16
NORTHWESTERN POLYTECHNICAL UNIV
View PDF5 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a D2D network caching strategy method based on deep reinforcement learning, which solves the pr...

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
  • Cache strategy method in D2D network based on deep reinforcement learning
  • Cache strategy method in D2D network based on deep reinforcement learning
  • Cache strategy method in D2D network based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0093] In this embodiment, a caching-enabled D2D network with 200 D2D users is considered, and selected content is distributed to D2D storage based on content popularity and user mobility prediction results. In order to simplify the simulation, in the deep reinforcement learning environment, the number of D2D users who satisfy user requests at each moment is set to a fixed value of 4, the distance d∈(0,4), the gain g∈(0,4), and P=1. In practical applications, this variation varies with time, but does not affect the accuracy of the algorithm.

[0094] Such as figure 1 Shown is the convergence performance graph of the present invention based on the deep reinforcement learning algorithm at different learning rates. It can be seen from the graph that the reward value of the system gradually tends to a stable value as time increases. Under the same training environment, the smaller the learning rate, the better the network performance of the system. When the learning rate is 0.01...

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 cache strategy method in a D2D network based on deep reinforcement learning. The method comprises the steps of acquiring position information of each user at a next moment via an echo state network algorithm by using the historical position information of each user in the cached and enabled D2D network as input data; acquiring content request information of each user at the next moment via the echo state network algorithm according to the position information of each user at the next moment in combination with the context information of each user at a current moment;caching the content request information into a cache space of the corresponding user; and acquiring an optimal strategy for delivering the content request information between the users in the cached and enabled D2D network via a deep reinforcement learning algorithm by minimizing the transmission power of the user transmitting the content request information and minimizing the delay of the user receiving the content request information as targets. According to the method provided by the invention, the problems that in the cached and enabled D2D network, the placement hit rate of the cached content is low and the consumed energy is large and the delay is long during a cache delivery process are solved.

Description

【Technical field】 [0001] The invention belongs to the technical field of cache-enabled D2D network cache transmission, and in particular relates to a cache strategy method in a D2D network based on deep reinforcement learning. 【Background technique】 [0002] In recent years, device-to-device (D2D) communication has attracted widespread attention in 5G wireless networks. This technology enables users to achieve direct communication within a certain distance without the assistance of base stations, and can effectively improve energy efficiency and Spectral efficiency. [0003] However, as the number of wireless device users increases exponentially, resulting in high traffic loads, this greatly increases backhaul link costs and transmission delays. The caching technology can eliminate repeated data transmission of popular content, reduce backhaul traffic and improve network throughput, and has become a strong candidate for 5G development. [0004] Considering the limited avai...

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): H04L29/08G06N3/08
CPCG06N3/08H04L67/5682H04L67/568
Inventor 李立欣徐洋李旭高昂梁微殷家应
Owner NORTHWESTERN POLYTECHNICAL UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap