Patent · US Active

Active edge caching method based on community discovery and weighted federated learning

US11943114B1 · kind B1 · utility

0Cited by
0References
9Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 1, 2023
Grant dateMar 26, 2024
Priority date
Expiry dateJun 1, 2043

Classification

  • Technology area (CPC Y)Emerging Cross-Sectional Technologies
  • CPC primaryY02D30/70
  • WIPO fieldDigital communication
  • WIPO sectorElectrical engineering

Abstract

An active edge caching method based on community discovery and weighted federated learning for selecting an optimal caching user and developing an optimal caching strategy; user grouping method based on community discovery is first provided, users are divided into different user groups according to users' mobility and social attributes, degrees of importance of different users are computed in each user group, and most important user is selected as a caching node to provide content distribution services; a content popularity prediction framework based on attention weighted federated learning is provided for combining attention weighted federated learning mechanism with deep learning algorithm to predict future user preferences for different content, so as to improve content popularity prediction accuracy and solve user privacy disclosure; finally, hot content is cached on selected caching users according to prediction results, to achieve goals of reducing network transmission latency and network operation cost.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.