• Home
  • Search
  • Evaluation of Thermal Stress on Heterogeneous IoT-Based Federated Learning
  • https://doi.org/10.3390/electronics13163140Copy DOI Icon

Evaluation of Thermal Stress on Heterogeneous IoT-Based Federated Learning

Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Similar Papers
Abstract

Federated learning is a novel paradigm allowing the training of a global machine-learning model on distributed devices. It shares model parameters instead of private raw data during the entire model training process. While federated learning enables machine learning processes to take place collaboratively on Internet of Things (IoT) devices, compared to data centers, IoT devices with limited resource budgets typically have less security protection and are more vulnerable to potential thermal stress. Current research on the evaluation of federated learning is mainly based on the simulation of multi-clients/processes on a single machine/device. However, there is a gap in understanding the performance of federated learning under thermal stress in real-world distributed low-power heterogeneous IoT devices. Our previous work was among the first to evaluate the performance of federated learning under thermal stress on real-world IoT-based distributed systems. In this paper, we extended our work to a larger scale of heterogeneous real-world IoT-based distributed systems to further evaluate the performance of federated learning under thermal stress. To the best of our knowledge, the presented work is among the first to evaluate the performance of federated learning under thermal stress on real-world heterogeneous IoT-based systems. We conducted comprehensive experiments using the MNIST dataset and various performance metrics, including training time, CPU and GPU utilization rate, temperature, and power consumption. We varied the proportion of clients under thermal stress in each group of experiments and systematically quantified the effectiveness and real-world impact of thermal stress on the low-end heterogeneous IoT-based federated learning system. We added 67% more training epochs and 50% more clients compared with our previous work. The experimental results demonstrate that thermal stress is still effective on IoT-based federated learning systems as the entire global model and device performance degrade when even a small ratio of IoT devices are being impacted. Experimental results have also shown that the more influenced client under thermal stress within the federated learning system (FLS) tends to have a more major impact on the performance of FLS under thermal stress.

Loading PDF

Similar Papers
  • PDF
  • Conference Article
  • Citations3

Evaluation of Thermal Stress on IoT-based Federated Learning

  • Apr 18, 2024
  • Yi Gu +3
  • Conference Article
  • Citations23

Non-Orthogonal Multiple Access in a mmWave Based IoT Wireless System with SWIPT

  • Jun 01, 2017
  • Haijian Sun +3
  • Conference Article
  • Citations3

GaaS: Adaptive Cross-Platform Gateway for IoT Applications

  • Nov 01, 2019
  • Mohamed Abdelaal +4
  • Conference Article
  • Citations1

Performance Evaluation of Lightweight Cryptographic Algorithms on RISC-V

  • May 15, 2022
  • Muhammet Cihat Mumcu +2
  • Research Article
  • Citations1

Connecting food supply chains

  • Sep 01, 2022
  • Food Science and Technology
  • Research Article

Classification of cyber threats for internet of things

  • Dec 15, 2023
  • Bulletin of the National Engineering Academy of the Republic of Kazakhstan
  • S T Tleuberdin +1
  • Conference Article
  • Citations29

Comparison of Lossless Data Compression Techniques in Low-Cost Low-Power (LCLP) IoT Systems

  • Dec 01, 2019
  • Aravind Hanumanthaiah +4
  • Conference Article
  • Citations19

PaperW8

  • Aug 25, 2020
  • Calvin Brierley +4
  • Research Article
  • Citations5

Toward Automatically Connecting IoT Devices with Vulnerabilities in the Wild

  • Oct 19, 2023
  • ACM Transactions on Sensor Networks
  • Jinke Song +5
  • Research Article
  • Citations3

A Lightweight Received Signal Strength Indicator Estimation Model for Low-Power Internet of Things Devices in Constrained Indoor Networks

  • Mar 24, 2025
  • Applied Sciences
  • Samrah Arif +2
  • PDF
  • Research Article
  • Citations12

A generic Internet of things (IoT) platform supporting plug-and-play device management based on the semantic web

  • Sep 10, 2019
  • Journal of Ambient Intelligence and Humanized Computing
  • Woongsup Kim +5
  • Research Article
  • Citations31

Investigation on identify the multiple issues in IoT devices using Convolutional Neural Network

  • Oct 12, 2022
  • Measurement: Sensors
  • Swapna Thouti +4
  • Research Article
  • Citations62

Leveraging Electromagnetic Side-Channel Analysis for the Investigation of IoT Devices

  • Jul 01, 2019
  • Digital Investigation
  • Asanka Sayakkara +2
  • Research Article
  • Citations26

A framework for DNS naming services for Internet-of-Things devices

  • Jan 31, 2018
  • Future Generation Computer Systems
  • Keuntae Lee +5
  • Research Article
  • Citations2

A Practical Evaluation of a Federated Learning Application in IoT Device and Cloud Environment

  • Jan 17, 2025
  • Journal of the Brazilian Computer Society
  • Guilherme Nunes Nasseh Barbosa +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.