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

Smart factory-oriented random access resource optimization method and device

A random access and resource optimization technology, applied in the field of wireless communication, can solve problems such as network congestion and overload resolution, and unsatisfactory results

Active Publication Date: 2021-10-08
UNIV OF SCI & TECH BEIJING
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a random access resource optimization method and device for smart factories, so as to solve the network problems caused by massive access requests in the industrial Internet in the M2M communication scenario based on the ACB mechanism. Congestion and overload problem solving effect is not ideal

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
  • Smart factory-oriented random access resource optimization method and device
  • Smart factory-oriented random access resource optimization method and device
  • Smart factory-oriented random access resource optimization method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0050]In the M2M communication scenario of the smart factory, in order to solve the problem of network congestion and overload caused by the massive access requests in the industrial Internet, this embodiment provides a smart factory-based federated learning, reinforcement learning and dynamic access priority random access resource optimization method. The main idea of ​​this method is to effectively control the access problem of massive equipment in industrial intelligent manufacturing by introducing the ACB mechanism based on dynamic priority, prioritize the business according to the delay sensitivity, and adopt the back-off and retransmission mechanism to alleviate the problem. Network congestion problem. Furthermore, the efficient allocation of random access preamble resources is realized by combining federated learning and deep reinforcement learning. The local end adopts deep reinforcement learning to train the agent, and uses the DQN experience playback method to store...

no. 2 example

[0088] This embodiment provides a random access resource optimization device for smart factories, the device includes:

[0089] The business access priority division module is used to divide the priority of each business access according to the delay sensitivity of each business in industrial production;

[0090] The federated reinforcement learning module is used to train the local model using the reinforcement learning algorithm at the local end; and uses the federated learning algorithm on the cloud to perform global model aggregation on the local model parameters of each local end to establish a shared machine learning model; The goal of using the learning algorithm to train the local model is: based on the classification results of the service access priority classification module for each service access priority, on the premise of ensuring the service quality requirements of various services, maximize the number of successful user access ;

[0091] The random access res...

no. 3 example

[0094] This embodiment provides an electronic device, which includes a processor and a memory; at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor, so as to implement the method of the first embodiment.

[0095] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein at least one instruction is stored in the memory, so The above instruction is loaded by the processor and executes the above method.

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 smart factory-oriented random access resource optimization method and device. The method comprises the following steps: dividing the access priority of each service according to the delay sensitivity of different services; training a local model at a local end by adopting a reinforcement learning algorithm; carrying out global model aggregation on the local model parameters of each local end by adopting a federal learning algorithm at the cloud end, and establishing a shared machine learning model, wherein the reinforcement learning target is to maximize the number of successfully accessed users on the premise of ensuring the service quality requirements of various businesses; and utilizing the optimized shared machine learning model to realize access resource allocation, so that the system throughput is maximized and the overall production efficiency of a factory is improved on the premise of meeting the service quality requirements of various businesses. According to the invention, the resource utilization rate can be optimized and the network performance can be improved on the premise of meeting the delay requirements of various services in industrial production.

Description

technical field [0001] The present invention relates to the field of wireless communication technology, in particular to a method and device for optimizing random access resources for smart factories. Background technique [0002] With the rapid transformation of the industrial manufacturing industry towards digitalization, networking, and intelligence, the large-scale access of dense industrial equipment has caused serious network congestion problems in the production and operation of factories. [0003] Therefore, how to maximize the system throughput by rationally allocating access resources is one of the urgent problems to be solved in smart factories. [0004] In recent years, the congestion control scheme based on the Access Class Barring (ACB) mechanism has been widely used in the field of wireless communication. The solution to network congestion and overload problems caused by access requests is not satisfactory and needs to be improved. Contents of the invention...

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): H04W4/70H04W24/02H04W74/08G06N3/04G06N3/08G06N20/00
CPCH04W4/70H04W24/02H04W74/0833G06N3/08G06N20/00G06N3/045Y02P90/30
Inventor 张海君姜铭慧刘向南隆克平
Owner UNIV OF SCI & TECH BEIJING
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com