Underwater acoustic cooperative communication routing method based on reinforcement learning Sarsa algorithm

A technology of reinforcement learning and cooperative communication, which is applied in wireless communication, sustainable communication technology, ultrasonic/sonic wave/infrasonic transmission system, etc., can solve the problems of non-reinforced learning Sarsa algorithm application, etc., to increase the selection space and improve transmission efficiency , the effect of reducing energy consumption

Active Publication Date: 2021-03-09
XIAMEN UNIV +1
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the underwater acoustic communication network, most of the current research is on the algorithm optimization in the non-cooperative node network, such as the depth-based routing protocol DBR and the vector-based routing protocol VBF. The appl...

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 acoustic cooperative communication routing method based on reinforcement learning Sarsa algorithm
  • Underwater acoustic cooperative communication routing method based on reinforcement learning Sarsa algorithm
  • Underwater acoustic cooperative communication routing method based on reinforcement learning Sarsa algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0036] According to the underwater acoustic communication energy consumption model, combined with cooperative communication technology, the present invention utilizes the reinforcement learning Sarsa algorithm to quickly find the cooperative route with the least energy consumption in the underwater acoustic multi-hop cooperative communication network, including the following steps:

[0037] 1) if figure 1 , design an underwater acoustic communication network topology, randomly arrange 50 nodes, node 1 is the source node S, node 50 is the target node D;

[0038] 2) Parameter initialization: the maximum number of iterations is k=10000, the current number of iterations is i=1, the initial Q value Q(x,a)=0, the initial state of the agent is x i = 1, learning rate α = 1, discount factor γ = 0.8, exploration rate

[0039] 3) Design reward mecha...

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 acoustic cooperative communication routing method based on a reinforcement learning Sarsa algorithm, and relates to an underwater acoustic network. The method comprises the steps: considering two aspects of reducing underwater acoustic data transmission energy consumption and complexity of a route selection algorithm, and providing route selection for an underwater acoustic multi-hop cooperative communication network by utilizing a reinforcement learning Sarsa algorithm according to an underwater acoustic communication energy consumption model; under the complex condition that a relay node and a cooperative node exist at the same time, rapidly carrying out the underwater acoustic multi-hop cooperative communication network route selection under the condition that the marine environment dynamically changes. A reinforcement learning algorithm is combined with cooperative communication, the operation complexity can be effectively reduced, the route selection stability is enhanced, and the transmission efficiency is improved, so that a cooperative route line enabling the total energy consumption of system transmission to be lowest is obtained, theenergy consumption of an underwater acoustic data transmission system is effectively reduced, and the life cycle of an underwater acoustic communication network is prolonged.

Description

technical field [0001] The invention relates to an underwater acoustic network, in particular to an underwater acoustic cooperative communication routing method based on a reinforcement learning Sarsa algorithm. Background technique [0002] The earth is a "water sphere" composed of 71% water and 29% land. The origin of organisms is inseparable from the ocean. People have always been curious about the mysterious and vast ocean. From ancient times to the present, countless scientific researchers have focused on exploring this mysterious world, and the underwater acoustic communication network is an indispensable technical support in the process of exploring the ocean. At the same time, the development of underwater acoustic communication technology also plays an important role in the development of marine resources and maritime military power. [0003] Due to the constraints of the complex marine environment, the realization of underwater communication is more difficult than...

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): H04W40/08H04W40/22H04B11/00H04B13/02
CPCH04W40/08H04W40/22H04B11/00H04B13/02Y02D30/70
Inventor 陈友淦林姗朱建英陶毅张小康许肖梅
Owner XIAMEN 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