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

Edge computing resource allocation method

A technology of edge computing and resource allocation, applied in the field of resource allocation strategy, which can solve the problems of highly random and complex models

Pending Publication Date: 2020-10-23
XI AN JIAOTONG UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Regarding how to effectively allocate edge computing resources, the mobile edge computing environment can be modeled as a Markov decision process, which is highly stochastic and complex

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
  • Edge computing resource allocation method
  • Edge computing resource allocation method
  • Edge computing resource allocation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0071] In this part, we consider a specific edge computing model as follows:

[0072] The edge computing model is a scenario of a mobile edge computing node (MEC node) with C CPU cores, N buffers, N users, and N terminals. In this scenario, the user sends tasks to the edge computing node, and the edge computing node allocates CPU cores to process these tasks, and then sends the processing results to the terminal. Each frame of the model is divided into T f symbols, each symbol time is t s seconds, and one frame can be divided into three stages. Taking frame k as an example, in the first stage, user U n (n∈{1,2,...,N}) sends the size of data, time occupied symbol length, when the task is sent to the MEC node, the node stores the task in the buffer queue Buffer n; in the second stage, the MEC node allocates the computing resources of C CPU cores to the user, and the user who obtains the computing resource, The first task at the head of the queue in the corresponding buff...

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 belongs to the technical field of resource allocation strategies, and particularly relates to an edge computing resource allocation method. With regard to how to effectively allocate edge computing resources, a mobile edge computing environment can be modeled as a Markov decision process, while the model is highly random and very complex. The invention discloses an edge computing resource allocation method. The method comprises the following steps: 1) defining the state, action and reward of an edge computing model; 2) analyzing, namely defining a structure of a neural network and an input and output structure by utilizing the state, the action and the reward defined in the step 1); and 3) updating and training the neural network defined in the step 2) according to a given training method, and applying the neural network. A deep reinforcement learning technology in machine learning is very suitable for being applied to the model due to the strong perception ability and decision ability of the deep reinforcement learning technology to the environment, so as to solve the problem of return maximization.

Description

technical field [0001] The present application belongs to the technical field of resource allocation strategies, and in particular relates to an edge computing resource allocation method. Background technique [0002] With the rise of the fifth-generation mobile communication technology (5G), mobile applications and services have higher requirements for latency. The traditional cloud computing model can no longer fully meet the requirements of low latency. Mobile Edge Computing (MobileEdgeComputing ) technology followed. [0003] In the traditional cloud computing model, users upload computing-intensive tasks to the cloud server for processing through the core network. The transmission delay caused by factors is relatively large. In order to reduce the transmission delay, the mobile edge computing mode configures computing resources at the edge of the network, such as wireless access points such as base stations. At the same time, it also brings advantages such as saving ...

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): G06F9/50G06N3/04G06N3/08
CPCG06F9/5027G06N3/08G06N3/045
Inventor 袁新杰杜清河
Owner XI AN JIAOTONG 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

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