Unlock instant, AI-driven research and patent intelligence for your innovation.

Self-adaptive transmission method based on reinforcement learning in wireless sensor network

A wireless sensor, adaptive transmission technology, applied in transmission system, network topology, wireless communication and other directions, can solve problems such as radio interference, unreliable links, bad links, data packet conflicts, etc., to achieve low latency and good transmission reliability , the effect of low energy consumption

Inactive Publication Date: 2021-10-26
ZHEJIANG UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The second challenge is radio interference and packet collisions
The third challenge is spreading bad links due to unreliable links

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
  • Self-adaptive transmission method based on reinforcement learning in wireless sensor network
  • Self-adaptive transmission method based on reinforcement learning in wireless sensor network
  • Self-adaptive transmission method based on reinforcement learning in wireless sensor network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.

[0024] The learner agent of reinforcement learning, which is the wireless sensor node in this invention, how to take a series of actions in the environment, so as to obtain the maximum cumulative reward. Keep trying and delaying rewards are two very distinctive characteristics of reinforcement learning. Through continuous interaction with the environment, the feedback data enables the agent to continuously learn and choose actions that maximize benefits.

[0025] exist image 3 In the state transition diagram shown, P represents the current channel state and the probability that a single...

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 self-adaptive transmission method based on reinforcement learning in a wireless sensor network. The method comprises the following steps: conducting interaction between a communication network formed by wireless sensor nodes and an environment where the network is located; calculating the number of data packets to be sent in real time according to the current channel environment in combination with reinforcement learning; with state space being a channel state from a source node to a target node in the network and action space being a data packet multiplication number of a node, applying time from the time when the node sends a data packet to the time when the node receives the data packet or time set by a timeout timer as a return; and recalculating a real-time strategy for the number of data packets sent by each node via the node by using different data transmission actions and corresponding data transmission time returns.

Description

technical field [0001] The invention relates to the technical field of wireless communication, in particular to an adaptive transmission method based on reinforcement learning in a wireless sensor network. Background technique [0002] Reliable communication is crucial for most applications of wireless sensor networks (WSNs). A large number of sensor devices are widely used in environmental ecological monitoring, health monitoring, home automation, traffic control and other fields. In many safety-critical applications, a lack of emergency information can lead to severe property damage and personal injury, which is often unacceptable. Wireless sensor networks have the characteristics of high data redundancy and energy saving. In many cases, 100% reliable communication is expensive and unnecessary. Due to the openness of wireless channels, the efficiency and reliability of information transmission has become the focus of attention. In the case of poor channel conditions, t...

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): H04L1/16H04L5/00H04L12/24H04W84/18
CPCH04W84/18H04L5/0055H04L1/1607H04L41/12
Inventor 郑水华徐逸伦林伟周浩杰
Owner ZHEJIANG UNIV OF TECH