Time sequence regularization tensor decomposition-based QoS (Quality of Service) prediction method in mobile edge computing

A prediction method and time sequence technology, applied in constraint-based CAD, calculation, computer-aided design, etc., can solve problems such as inaccuracy, and achieve the effect of improving accuracy

Active Publication Date: 2021-09-21
XIAN UNIV OF POSTS & TELECOMM
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the method of predicting QoS in the prior art is not accurate

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
  • Time sequence regularization tensor decomposition-based QoS (Quality of Service) prediction method in mobile edge computing
  • Time sequence regularization tensor decomposition-based QoS (Quality of Service) prediction method in mobile edge computing
  • Time sequence regularization tensor decomposition-based QoS (Quality of Service) prediction method in mobile edge computing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] like figure 1 As shown, a QoS prediction method based on time series regularization tensor decomposition in mobile edge computing provided by the present invention includes:

[0070] S1, obtain the QoS record of the user access service;

[0071] S2, constructing a three-dimensional tensor model representing the relationship between users, services and time based on the QoS records;

[0072] Tensors are the generalization of vectors (first-order tensors) and matrices (second-order tensors) to higher-order sequences, and can be called multidimensional matrices or multidimensional arrays. As a powerful tool for high-dimensional data representation and analysis, it has been It is widely used in data mining, computer vision, image processing, traffic flow analysis and other research fields. Tensors are usually written in Euler letters Matrices are represented by uppercase letters X,Y…, vectors are represented by lowercase letters x,y…. an N-dimensional tensor can be c...

Embodiment approach

[0100] As an optional implementation manner of the present invention, the above step S3 includes:

[0101] Step 31: construct the first optimization problem with the smallest error between the approximate tensor of the predicted three-dimensional tensor model and the original tensor;

[0102] Step 32: When the QoS obtained by user i calling service j at time k is the same as the predicted QoS obtained by user i calling service j at time k, then under the condition that the first optimization problem is the smallest, transform the first optimization problem into the first optimization problem. Two optimization problems;

[0103] Step 33: Introduce the user dimension, the constraint regular terms related to the user dimension, the service dimension and the time dimension in the second optimization problem. The weights of the user, service and time of the three-dimensional tensor model are decomposed and constrained respectively, and the time series regularization is introduced. ...

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 a time sequence regularization tensor decomposition-based QoS (Quality of Service) prediction method in mobile edge computing. The method comprises the following steps of: acquiring a QoS record of a user access service; constructing a three-dimensional tensor model representing a user, service and time relationship based on the QoS record; using a CP decomposition method to decompose the three-dimensional tensor model, and introducing constraint regular terms related to a user dimension, a service dimension and a time dimension in the decomposition process to perform decomposition constraint on the weights of the user, the service and the time of the three-dimensional tensor model; and introducing a time sequence regular term to carry out decomposition constraint on a time sequence relation of a time dimension of the three-dimensional tensor model, respectively obtaining a user factor matrix, a service factor matrix and a time factor matrix, and predicting a QoS value of a specific service called by a specific user at a specific moment. According to the method, tensor decomposition and time sequence prediction are combined to improve the accuracy of QoS prediction in the mobile edge computing environment.

Description

technical field [0001] The invention belongs to the technical field of mobile edge, and in particular relates to a QoS prediction method based on time series regularization tensor decomposition in mobile edge computing. Background technique [0002] The rapid development of Mobile Edge Computing (MEC) technology has led to a dramatic increase in the number of mobile services, and many mobile services provided by different service providers have the same or similar functions. QoS data in motion has the following two special properties: high dimensionality and high sparsity of QoS data and dynamic variability of QoS data. [0003] High dimensionality and high sparsity means that more and more mobile services are developed in different domains and used to build complex mobile applications. At present, the number of users and mobile service objects that need to be processed is increasing rapidly, and the problem of high sparseness in service calls is more serious, and such high...

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): G06F30/20G06F17/16G06F111/04G06F119/12
CPCG06F30/20G06F17/16G06F2111/04G06F2119/12Y02T10/40
Inventor 夏虹陈彦萍张雅倩王忠民高聪金小敏王凤伟董庆义
Owner XIAN 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