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

Federal learning scheduling method based on calculation unloading in heterogeneous network

A heterogeneous network and scheduling method technology, applied in transmission systems, electrical components, etc., can solve the problems of not considering multi-edge servers and communication resource allocation, only considering a single edge server and client training capabilities, etc., to improve overall performance , reduce overhead, and optimize the effect of the effect

Active Publication Date: 2022-06-21
NANJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As an implementation of distributed machine learning, federated learning and edge computing have many intersections with each other. Many current inventions only consider the training capabilities of a single edge server and client itself, and do not consider multiple edges in heterogeneous network scenarios. Impact of server and communication resource allocation

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
  • Federal learning scheduling method based on calculation unloading in heterogeneous network
  • Federal learning scheduling method based on calculation unloading in heterogeneous network
  • Federal learning scheduling method based on calculation unloading in heterogeneous network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0108] The following examples may enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way.

[0109] see image 3 , a federated learning scheduling method based on computing offload in the heterogeneous network lower edge computing system of the present invention, comprising the following steps:

[0110] Step 1: Establish a federated learning model based on computing offload in a heterogeneous network multi-MEC system. In the system, users use local data to train to obtain sub-models, and send the sub-models to the central server on the macro base station, where users are aggregated on the central server. The sub-model can be used to obtain the global model. For users with limited resources who cannot complete local training in time, the local data can be offloaded to the edge server on the small base station for calculation.

[0111] Step 2: Comprehensively consider the energy consumption, time delay an...

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 federated learning scheduling method based on calculation unloading in a heterogeneous network, which comprises the following steps: firstly, a macro base station trains a machine learning model by using local data of a user, and the user can unload the data to an edge server near a small base station for calculation; then, the precision of federal learning and energy consumption and time delay generated in operation and communication are comprehensively considered, an optimization problem is established, and the optimization problem is divided into three sub-problems of optimizing local learning precision and unloading decision, user calculation frequency and user resource block allocation. Through simulation, the effects obtained under different parameter conditions are analyzed. Simulation results show that the method provided by the invention can effectively reduce the overhead in the training process.

Description

technical field [0001] The invention belongs to the technical field of wireless communication, and in particular relates to a federated learning scheduling method based on computing offload in a heterogeneous network. Background technique [0002] As the number of user terminals continues to increase, a large amount of personal data will be generated. These big data provide a solid material foundation for the rapid development of artificial intelligence. However, the data required in machine learning involves various types, belonging to different individuals and departments, and the data exists in the form of isolated islands. It takes a lot of communication resources to transmit these large amounts of data to a unified platform. In addition, considering the User privacy and data security issues, collecting and fusing this data will face many challenges. Federated learning can perform distributed data usage and machine learning modeling locally on the premise of user privac...

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): H04L41/14H04L41/0823H04L67/10
CPCH04L41/145H04L67/10H04L41/0823Y02D30/70
Inventor 朱琦王致远
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