Check patentability & draft patents in minutes with Patsnap Eureka AI!

Underwater multi-modal network routing strategy generation method based on improved reinforcement learning

A reinforcement learning and multi-modal technology, applied in the direction of specific environment-based services, advanced technology, electrical components, etc., can solve the problems of unanalyzed data transmission characteristics, data value balance, network energy consumption, high data transmission delay, and algorithm operation High energy consumption and other issues, to achieve the effect of reducing data transmission delay, speeding up convergence speed, and balancing network energy

Active Publication Date: 2021-02-09
TIANJIN UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although it can effectively reduce transmission delay and improve the success rate of data transmission, it does not analyze data transmission characteristics, data value, and balance network energy consumption; resulting in high energy consumption for algorithm operation, high transmission delay for some important data, and short network life And other issues

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
  • Underwater multi-modal network routing strategy generation method based on improved reinforcement learning
  • Underwater multi-modal network routing strategy generation method based on improved reinforcement learning
  • Underwater multi-modal network routing strategy generation method based on improved reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to describe the implementation mode more clearly, it is assumed that there are K data of the level of information value to be transmitted in the network; each node has G transmission frequency band combinations. The following is attached figure 1 , the specific manner, structure, features and functions of the underwater data routing strategy designed according to the present invention are described in detail as follows.

[0030] 1. Offline training phase

[0031] Step 1: The aggregation node (sink node) located on the water surface generates an advertisement packet (ADV packet) for each transmission frequency band combination; then the packet is sent out in the form of broadcast through the corresponding transmission frequency band combination, and the backoff time is T b =0 to start timing. The ADV contains the coordinate information of the sink node, and the backoff time T b , each level of information value is the final reward Re of the data s (1) and th...

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 underwater multi-modal network routing strategy generation method based on improved reinforcement learning, and the method comprises the following steps: in an offline stageat the initial stage of routing strategy implementation, preliminarily learning a transmission relation between network nodes from a water surface aggregation node in an iteration mode, so that eachnode obtains the maximum transmission revenue from each piece of information value quantity grade data to the aggregation node; in the online stage of network operation, using relay node and transmission frequency band combination for each node through a reinforcement learning model to obtain the expected revenue of the water surface aggregation node, so that transmission paths suitable for different information value grade data are constructed. According to the method, high-information-value-quantity data transmission time delay is reduced; the network energy consumption is reduced and balanced, and the network operation time is prolonged.

Description

technical field [0001] The invention mainly relates to the technical field of underwater wireless sensor networks, in particular to a method for generating routing strategies for underwater multi-modal networks based on improved reinforcement learning. Background technique [0002] Underwater wireless sensor networks can help humans understand and understand the ocean more conveniently, obtain valuable ocean data information, improve the ability to monitor and predict the ocean environment, and the ability to deal with ocean emergencies. It can serve a wide range of applications, such as marine information collection, environmental monitoring, deep-sea exploration, disaster prediction, auxiliary navigation, distributed tactical monitoring, etc. Various marine applications are increasing day by day. Due to the differences in application types and time sensitivities, their requirements for marine data transmission performance are often different. Suppliers of underwater wirel...

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): H04W4/38H04W40/04H04W40/24
CPCH04W4/38H04W40/04H04W40/24Y02D30/70
Inventor 刘春凤赵昭曲雯毓广晓芸余涛
Owner TIANJIN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com