Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Wireless sensor network topology optimization method based on asynchronous deep reinforcement learning

A wireless sensor and reinforcement learning technology, applied in network topology, neural learning methods, network planning, etc., can solve the problems of data optimization results oscillation, dependence on computing resources, etc., to speed up the convergence time, improve the ability to resist attacks, improve communication effect of ability

Active Publication Date: 2020-11-13
TIANJIN UNIV
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, the journal "Deep Actor-Critic Learning-basedRobustness Enhancement of Internet of Things" proposes a strategy for intelligent wireless sensor network topology based on deep reinforcement learning, but in the process of running the model, it is very dependent on GPU computing resources. Moreover, the isomorphism of the data will lead to the oscillation of the optimization results.

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
  • Wireless sensor network topology optimization method based on asynchronous deep reinforcement learning
  • Wireless sensor network topology optimization method based on asynchronous deep reinforcement learning
  • Wireless sensor network topology optimization method based on asynchronous deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The specific method, structure, features, and functions of the wireless sensor network topology optimization method designed according to the present invention are described in detail below in conjunction with the accompanying drawings.

[0019] Step 1: Use the rules of the scale-free network model to generate the initialized wireless sensor network topology X. The network topology nodes are randomly deployed, and the nodes newly added to the wireless sensor network are connected according to the edge density parameter M. Newly added nodes are connected to existing nodes with high probability first, ensuring that the wireless sensor network can describe the network topology characteristics of the real world to the greatest extent, and at the same time, the geographic location P of the node is fixed. Each node has the same attributes.

[0020] Among them, setting the edge density parameter to M=2 means that the number of edges in the wireless sensor network is twice the numb...

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 wireless sensor network topology optimization method based on asynchronous deep reinforcement learning. The method comprises the following steps: a step of generating an initialized wireless sensor network topology structure by utilizing a rule of a scale-free network model; a step of compressing the topological structure of the wireless sensor network; a step of initializing an asynchronous deep reinforcement learning model; a training and testing stage; a training stage, wherein firstly, a wireless sensor network topological structure is serialized, and a row vectoris used for representing the wireless sensor network topological structure; then, respectively inputting the row vectors of the network topology structure into different local network training models; secondly, the local network training model comprises two neural network models, namely an action selection strategy network and a strategy evaluation network; a test stage wherein the global networktraining model performs test evaluation on the test data set; a step of repeating the steps 1, 2, 3 and 4 till the maximum number of iterations is reached.

Description

Technical field [0001] The present invention relates to the present invention mainly relates to the technical field of wireless sensor network, in particular to a wireless sensor network topology optimization method based on asynchronous deep reinforcement learning. Background technique [0002] As an important network component of the Internet of Things in smart cities, wireless sensor networks play an important role in obtaining information in real time, enabling people to obtain more information they want. By analyzing these data, the service quality of smart cities can be improved and people can deal with emergencies. Wireless sensor networks are widely used, such as smart homes, smart wearable devices, smart transportation, environmental monitoring, homeland security, border detection, etc. The premise of the above application is that the network has high robustness and can send the sensed data to the server data center through the network, and relevant personnel or systems...

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): H04W16/18H04W24/02H04W24/06G06K9/62G06N3/08H04W84/18
CPCH04W16/18H04W24/02H04W24/06G06N3/08H04W84/18G06F18/214
Inventor 邱铁陈宁李克秋周晓波赵来平张朝昆
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products