End-to-end network slice resource allocation algorithm based on deep reinforcement learning

A technology for reinforcement learning and resource allocation, applied in the field of communication networks

Active Publication Date: 2020-09-18
NANJING UNIV OF POSTS & TELECOMM
View PDF7 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for a slice, only when the entire end-to-end lin

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
  • End-to-end network slice resource allocation algorithm based on deep reinforcement learning
  • End-to-end network slice resource allocation algorithm based on deep reinforcement learning
  • End-to-end network slice resource allocation algorithm based on deep reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0104]The present invention designs an end-to-end network slicing resource allocation algorithm based on deep reinforcement learning. This method comprehensively considers the access side and the core side, dynamically and reasonably allocates resources, and aims to improve the access rate of the system. In order to obtain the best resource allocation strategy, the factors that affect the access rate in the environment are trained using deep reinforcement learning to obtain a network model. In order to solve the value of the access rate under the determination of wireless resource allocation, an end-to-end resource mapping algorithm is designed for the access side and the core side. With these prerequisites, it is possible to use the trained network to reasonably manage the dynamically changing environment Resource allocation. The specific implementation method is as follows:

[0105] 1. End-to-end model and wireless resource initialization

[0106] A. End-to-end model acces...

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 provides an end-to-end network slice resource allocation algorithm based on deep reinforcement learning (DQN) for the situation that multiple slices of a hybrid service share wireless resources, which algorithm dynamically and reasonably allocates the resources by jointly considering the influence of an access side and a core side from an end-to-end perspective. In order to obtain areasonable DQN network through training, feedback of an environment in the DQN is solved, an end-to-end system access rate optimization problem is decoupled into an access side part and a core side part, and then a dynamic knapsack algorithm and a maximum access link mapping algorithm are designed respectively to obtain maximum end-to-end access. According to the method, resources can be dynamically adjusted by utilizing the trained network no matter in a static environment or a dynamic environment, so that the system access rate is remarkably improved.

Description

technical field [0001] The invention discloses an end-to-end network slicing resource allocation algorithm based on deep reinforcement learning, which can be applied to 5G networks for resource allocation in scenarios containing multiple services. The invention belongs to the technical field of communication network. Background technique [0002] 5G networks will support a large number of diverse business scenarios from vertical industries, such as smart security, high-definition video, smart home, autonomous driving, and augmented reality, etc. These business scenarios usually have different communication requirements. Traditional mobile communication networks are mainly used to serve a single mobile broadband service and cannot adapt to the diversified business scenarios of 5G in the future. If a dedicated physical network is built for each business scenario, it will inevitably lead to problems such as complex network operation and maintenance, high cost, and poor scalabi...

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): H04W24/02H04W24/06H04W28/16H04W72/02H04W72/04
CPCH04W24/02H04W24/06H04W28/16H04W72/02H04W72/53Y02D30/70
Inventor 朱晓荣李泰慧
Owner NANJING UNIV OF POSTS & TELECOMM
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap