Vehicle-mounted ad hoc network routing clustering method based on deep learning

A vehicle self-organization and deep learning technology, applied in network planning, network topology, advanced technology, etc., can solve problems such as high network energy consumption, unreliable operation of vehicle self-organization network, unstable routing path, etc., and achieve balanced energy consumption , Energy consumption reduction, the effect of reducing energy consumption

Inactive Publication Date: 2018-08-21
NANJING UNIV OF POSTS & TELECOMM
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Technical problem: The present invention proposes a highly reliable vehicular ad hoc network routing clustering method based on deep learning to solve the problems of unstable routing paths and high network energy consumption in vehicular ad hoc Unreasonable selection of head nodes and redundant data problems, which will lead to unreliable operation of VANETs

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
  • Vehicle-mounted ad hoc network routing clustering method based on deep learning
  • Vehicle-mounted ad hoc network routing clustering method based on deep learning
  • Vehicle-mounted ad hoc network routing clustering method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] according to figure 1 , a highly reliable vehicle-mounted self-organizing network clustering method based on deep learning of the present invention, the specific implementation method is:

[0043] 1. Deployment related to clustering and data transmission of vehicle ad hoc network

[0044] Assume that the current VAN routing is composed of a convergence node and N vehicle nodes, the location of the convergence node is fixed, and the vehicle nodes move randomly. Vehicle nodes are firstly evenly deployed in a square area with side length L, each node has a unique number, and the wireless communication range is R.

[0045] 1.1) Calculate the optimal number of cluster head nodes

[0046] 1.2) Divide the vehicular ad hoc network deployment range into m equal-area areas on average, and establish corresponding node sets for the m areas at the converging node, denoted as Node i , i=1,2,3...m. For any node N j , j=1,2,3...N, if N j ∈Node i , then N j Add to the correspo...

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 provides a high-reliability vehicle-mounted ad hoc network routing clustering method based on deep learning. The method comprises the following steps: performing reasonable clustering onnetwork nodes by using a custom clustering algorithm for a vehicle-mounted ad hoc network routing protocol, then fusing the data collected by the network nodes by using a deep learning algorithm, andfinally forming a low-energy and high-reliability clustering protocol. By adoption of the high-reliability vehicle-mounted ad hoc network routing clustering method provided by the invention, the problem of redundant data transmission and energy consumption unevenness of the vehicle-mounted ad hoc network nodes can be solved, the energy consumption of the vehicle-mounted ad hoc network nodes is reduced, and the life cycle is prolonged.

Description

technical field [0001] The invention relates to a node clustering and data fusion method in the working process of a vehicle-mounted self-organizing network. Through the analysis of node attributes and the training and learning of node data respectively, a vehicle-mounted self-organizing network clustering structure is formed and node redundant information transmission is optimized to ensure The vehicle-mounted self-organizing network is energy-saving, reliable and efficient, and belongs to the cross-technical fields of Internet of Things technology, deep learning technology and distributed processing. Background technique [0002] Deep learning is a new field in machine learning research. It is a derivative of neural network algorithms. It has achieved very good results in the classification and recognition of rich media such as images and voices. It imitates the mechanism of the human brain to interpret data. By combining low-level features to form more abstract high-level...

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): H04W40/10H04W40/20H04W84/18H04W16/22
CPCH04W16/22H04W40/10H04W40/20H04W84/18Y02D30/70
Inventor 陈志龚凯岳文静王福星
Owner NANJING UNIV OF POSTS & TELECOMM
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