V2X resource allocation method based on deep neural network

A deep neural network and resource allocation technology, applied in neural learning methods, biological neural network models, services based on specific environments, etc., can solve problems such as high algorithm complexity, inability to meet V2V requirements, etc., to ensure QoS and high reliability. Communication requirements, the effect of low latency

Active Publication Date: 2020-06-23
SHANGHAI UNIV
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the algorithm complexity of the existing technology is too high to meet the needs of V2V

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
  • V2X resource allocation method based on deep neural network
  • V2X resource allocation method based on deep neural network
  • V2X resource allocation method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Such as figure 1 As shown, this embodiment includes the following steps:

[0030] Step 1) Initial parameters: Select the algorithm verified in the urban scene based on the Manhattan grid of a single cell. When there are 5 C-UEs, 10 V-UEs, and the transmit power of the C-UE and the transmit power of V-UE Both are 23dBm, the lower limit of V2I link capacity 0.5bps / HZ, noise power N 0 is -114dBm, the average packet size B is 6400bits, and the maximum delay L is 100ms. The channel models selected for V2V and V2I links are shown in the following table:

[0031]

[0032] Step 2) Training parameters: According to the settings in step 1, the transmission power allocation and spectrum resource allocation in the case of maximizing the target value are obtained through the ergodic algorithm as the labels for neural network training, and the channel gain matrix under each group of allocations is used as the neural network. The input of the network is fed into the neural ...

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 V2X resource allocation method based on a deep neural network. The method comprises the steps: constructing a resource allocation problem according to the V2X communication model; therefore, a channel gain matrix is obtained as a sample to train a neural network; carrying out multi-classification processing of spectrum resource allocation and regression processing of transmitting power allocation by adopting the trained neural network in a real-time environment; according to the invention, the reliability and time delay of V2V communication are fully considered duringmodel establishment; a resource allocation problem is converted into a multi-allocation problem and a regression problem in deep learning, joint optimization is carried out by using one network, a classification problem and a regression problem are solved at the same time, spectrum resource and transmitting power allocation is carried out in real time under the condition of low complexity, and the method is suitable for an actual vehicle communication system.

Description

technical field [0001] The present invention relates to a technology in the field of mobile communication, in particular to a V2X resource allocation method based on a deep neural network. Background technique [0002] Cellular network-based vehicle-to-vehicle (V2V) direct communication reuses cellular uplink spectrum resources for vehicle-to-infrastructure (V2I) communication. However, while this method alleviates the pressure on spectrum resources, it also brings serious in-band interference, that is, V2V communication will interfere with V2I communication using the same spectrum resources, and V2I communication will also interfere with V2V direct communication, which affects the resources of V2X communication. It brings great difficulties in the study of allocation problems. The research on the resource allocation problem of V2X communication usually has complex algorithms, and it is difficult to obtain optimal allocation in the case of low complexity. [0003] In the p...

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 Applications(China)
IPC IPC(8): H04W52/14H04W52/24H04W52/26H04W52/38H04W72/04H04W72/08G06N3/08G06N3/04H04W4/44H04W4/46
CPCH04W52/146H04W52/243H04W52/267H04W52/383H04W72/044G06N3/08H04W4/44H04W4/46G06N3/045H04W72/541
Inventor 陈咪咪陈嘉君陈小静张舜卿徐树公
Owner SHANGHAI 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