Federated Learning for Privacy Preservation and Energy Efficiency Optimization in IoT End Devices

Read full text Summarise with VIRAT
Authors: Hongyu Mao
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Due to the large-scale deploying of the Internet of Things (IoT) end devices, data collection and transmission are suffering from serious privacy leakage threats, while the limited computing power and battery capability of terminal devices are also causing energy efficiency bottleneck. Due to this, as a distributed machine learning paradigm where data “do not leave the local area”, Federated Learning (FL) has application significance in solving the aforementioned issues. This paper primarily carries out research on the design of FL privacy preserving mechanism and energy efficiency optimization mechanism in IoT end-device. It explains theoretical models of FL, IoT end-device, and privacy-preserving technology, and discusses four optimization directions of FL privacy preserving from the aspects of model lightening, terminal-edge joint training, privacy preservation energy efficiency optimization and dynamic resource scheduling. The work gives theory guidance for safe and efficient IoT end devices’ running, so that these end devices can be more practical implemented with a large number.

Fields of Study & Subjects

Privacy-Preserving Technologies in Data IoT and Edge/Fog Computing Internet of Things and AI

Publication details

Journal / source
Academic Journal of Science and Technology
Volume
20
Issue
2
Pages
762–767
Publication date
30 March 2026
Language
EN