Resource allocation method and system for multitask federated learning in 5G network

A technology of resource allocation and multi-tasking, applied in the field of machine learning, it can solve the problems that affect algorithm performance and convergence speed, affect the quality and correctness of federated learning parameter updates between users, and unreliable wireless channels, so as to ensure efficiency and accuracy. sexual effect

Pending Publication Date: 2022-01-07
SHANDONG ELECTRIC POWER ENG CONSULTING INST CORP
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, symbol errors introduced by the unreliable nature of wireless channels and resource constraints can affect the quality and correctness of federated learning parameter updates among users
Such errors will affect the performance and convergence speed of the algorithm

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
  • Resource allocation method and system for multitask federated learning in 5G network
  • Resource allocation method and system for multitask federated learning in 5G network
  • Resource allocation method and system for multitask federated learning in 5G network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] In the multi-task-oriented learning process, there will be great differences in the execution time of different devices on different tasks, the amount of task input and output data, and task accuracy standards. It is necessary to comprehensively consider all aspects to ensure the total delay, energy or accuracy. The rate and other aspects have been optimized. This embodiment provides a user selection and resource allocation method for 5G multi-task federated learning.

[0053] The system environment is based on the 5G ultra-dense network scenario, and the specific architecture is as follows: figure 1 As shown, multiple user equipments are in the coverage area of ​​the base station. Among them, the number of users is M, the user set is M=={1,2,3,...,M}, the number of task categories to be learned is J, and the set of federated learning task categories is J=={1,2 ,3,...,J}. All federated learning task categories that exist in the system need to be executed. All tasks e...

Embodiment 2

[0124] The purpose of this embodiment is to provide a resource allocation system for multi-task federated learning in a 5G network. The system includes:

[0125] The equipment data volume acquisition module is used to acquire the corresponding equipment operating parameters, local training data volume and transmission data volume for each equipment training task;

[0126] The device restriction acquisition module is used to determine the time delay and energy consumption required for each device to transmit each task in combination with the network environment parameters, the transmit power of each device and the device parameters;

[0127] The device screening module is used to screen the devices participating in this round of federated learning according to the time delay and energy consumption required for each device to transmit each task to the base station during each round of training tasks;

[0128] The resource allocation module is configured to allocate resources for...

Embodiment 3

[0130] The purpose of this embodiment is to provide an electronic device.

[0131] An electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the program, it implements multitasking in the 5G network as described in Embodiment 1 A Resource Allocation Approach for Federated Learning.

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 multi-task federated learning-oriented resource allocation method and system in a 5G network. The method comprises the following steps of obtaining equipment operation parameters, local training data volume and transmission data volume corresponding to each task trained by each equipment; in combination with the network environment parameters, determining the transmitting power of each device and the device parameters, time delay and energy consumption required by each device for transmitting each task; during each round of training task, screening equipment participating in the round of federated learning according to time delay and energy consumption required for transmitting each task to the base station by each piece of equipment; and on the premise of limiting the sending power of the selected equipment, carrying out resource allocation of data transmission. According to the invention, based on the network communication environment, the equipment time delay and the energy consumption limiting conditions, equipment selection participating in learning and network transmission resource allocation are carried out for each round of federated learning, so the efficiency and accuracy of federated learning are ensured.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a resource allocation method and system for multi-task federated learning in a 5G network. Background technique [0002] With the rapid advancement of smart grid construction, there are more and more various power transmission and transformation equipment in the power system, and most of the equipment is placed outdoors. Normal maintenance monitoring and abnormal safety events mainly rely on manual discovery. Environmental factors such as environmental factors pose a huge challenge to traditional manual inspections. Smart cameras, inspection robots and other smart devices are constantly being put into use. The use of image recognition technology in smart devices can effectively improve the safety production capacity of all-weather smart monitoring stations and ensure the safety of workers in the environment. For example, the computing task is lowered to the smart camera...

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): G06F9/50G06N20/00
CPCG06F9/5027G06N20/00Y02D10/00
Inventor 孙海蓬黄萍李艳丽刘明刚王海洋张波苏俊浩刘政强
Owner SHANDONG ELECTRIC POWER ENG CONSULTING INST CORP
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