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

5G network slice resource allocation method and system

A technology of resource allocation and network slicing, applied in the field of communication network, can solve the problem that the delay characteristic requirements of uRLLC services cannot be guaranteed, and achieve the effect of guaranteeing the delay characteristic requirements and reducing the delay

Active Publication Date: 2021-12-10
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these technologies are basically unilaterally reducing the end-to-end delay of sliced ​​network services. At present, there is no technology that comprehensively solves the delay problem from multiple aspects, and some of these technologies are unreasonable, such as resource allocation. At first, the reinforcement learning technology used delay as the constraint condition instead of the optimization target. Although the delay was used as the optimization target later, the object of optimization was the average delay rather than the single service delay. This method cannot guarantee the time Delay characteristic requirements of uRLLC services with extremely high delay requirements

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
  • 5G network slice resource allocation method and system
  • 5G network slice resource allocation method and system
  • 5G network slice resource allocation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Such as figure 1 As shown, a 5G network slice resource allocation method includes:

[0055] Step 1: Obtain the slicing request proposed by the user, arrange the obtained slicing requests in groups according to the CoS level, and obtain 8 SFC queues;

[0056] Step 2: Take slice requests from the heads of the 8 SFC queues each time, and configure communication paths for the fetched slice requests according to the service classification of uRLLC, eMBB, and mMTC;

[0057] Step 3: Use the pre-learned resource allocation method to allocate computing resources, storage resources, and bandwidth resources for the fetched slice request, obtain a slice resource allocation strategy that meets the delay requirements of each service, and use it as the resource allocation method for slice requests;

[0058] Step 4: Delete the slice request that has completed resource allocation from the SFC queue, place the newly acquired slice request at the end of the corresponding SFC queue accord...

Embodiment 2

[0094] In this embodiment, the SAC algorithm that automatically adjusts the temperature coefficient α is taken as an example to illustrate the reinforcement learning process for implementing resource allocation.

[0095] In order to speed up the algorithm convergence process, the SAC algorithm introduces strategy entropy (using Indicates that it is calculated by the opposite number of the action probability), and its training process is as follows Figure 4 shown, including:

[0096] Step 1: Initialize the neural network.

[0097] Step 1.1: Initialize the neural network parameters.

[0098] Neural network parameters include: 1 policy network π with parameter φ; 2 action-value network Q with parameters θ 1 , θ 2 . The purpose of setting up two Q networks is to select the smaller one of the Q values ​​to avoid overestimation of the Q values. In order to reduce the data correlation, the two target networks corresponding to the two action-value networks Q are introduced, and...

Embodiment 3

[0119] This embodiment provides a 5G network slice resource allocation system, including:

[0120] Slicing grading module: used to fetch the slicing request proposed by the user, arrange the obtained slicing requests in groups according to the CoS level, and obtain 8 SFC queues;

[0121] Queue scheduling module: used to fetch slice requests from the queue leaders of the 8 SFC queues each time, and configure communication paths for fetched slice requests according to the service classification of uRLLC, eMBB, and mMTC;

[0122] Resource allocation module: It is used to allocate computing resources, storage resources, and bandwidth resources for the retrieved slice requests using the pre-learned resource allocation method, and obtain a slice resource allocation strategy that meets the delay requirements of each service, and use it as the resource allocation method for slice requests ;

[0123] Queue update module: It is used to delete the slice request that has completed resour...

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 5G network slice resource allocation method, and the method comprises the following steps: 1, acquiring slice requests proposed by a user, and arranging the acquired slice requests according to a CoS level to obtain eight SFC queues; 2, extracting slice requests from the head of the eight SFC queues each time, and configuring communication paths for the extracted slice requests according to the service classification of uRLLC, eMBB and mMTC; 3, allocating computing resources, storage resources and bandwidth resources to the extracted slice request by adopting a pre-learned resource allocation method; 4, deleting the slice request completing resource allocation from the SFC queue, placing the newly obtained slice request at the tail of the corresponding SFC queue according to the CoS level, and returning to the step 2. According to the method, the time delay is reduced from multiple aspects, different quantities of resources are allocated according to different time delay requirements of services, and the time delay characteristic requirements of various services are met on the premise that the resources are fully utilized.

Description

technical field [0001] The invention relates to a 5G network slice resource allocation method and system, belonging to the technical field of communication networks. Background technique [0002] At present, wireless communication has entered the 5G era. 5G services are divided into three categories: enhanced mobile broadband (eMBB), ultra-reliable and low-latency communications (uRLLC) and massive machine-type communications (mMTC) services. According to the requirements of different services for network characteristics, 5G communication networks will A physical network is divided into multiple virtual end-to-end networks to provide customized services for different businesses. The virtual end-to-end network includes sub-slices such as access network, bearer network, and core network. Compared with 4G services, 5G services have the characteristics of ultra-high speed, ultra-low latency, and large capacity. [0003] In order to solve the stringent requirements of delay, 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): H04W28/16H04L12/24H04W24/02
CPCH04W28/16H04L41/0893H04W24/02Y02D30/70
Inventor 杨国民
Owner NANJING UNIV OF POSTS & TELECOMM
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