Optimizing Federated Learning on TinyML Devices for Privacy Protection and Energy Efficiency in IoT Networks

Federated learning is presented as an effective solution to train artificial intelligence models on the Internet of Things networks without centralizing data, thus preserving privacy and minimizing security risks. However, its implementation in low-power devices, such as Tiny Machine Learning, faces...

Full description

Saved in:
Bibliographic Details
Main Authors: William Villegas-Ch, Rommel Gutierrez, Alexandra Maldonado Navarro, Aracely Mera-Navarrete
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10758420/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850146785644773376
author William Villegas-Ch
Rommel Gutierrez
Alexandra Maldonado Navarro
Aracely Mera-Navarrete
author_facet William Villegas-Ch
Rommel Gutierrez
Alexandra Maldonado Navarro
Aracely Mera-Navarrete
author_sort William Villegas-Ch
collection DOAJ
description Federated learning is presented as an effective solution to train artificial intelligence models on the Internet of Things networks without centralizing data, thus preserving privacy and minimizing security risks. However, its implementation in low-power devices, such as Tiny Machine Learning, faces significant challenges due to the processing, memory, and unstable connectivity limitations that characterize these environments. This study addresses these issues by developing a federated system optimized for Tiny Machine Learning devices, integrating differential privacy and encryption techniques adapted to their constraints. The methodology employed includes the evaluation of model precision and energy consumption in variable communication scenarios, as well as heterogeneous workloads. The results show that federated learning reduces energy consumption by 33% compared to the centralized approach, reaching an average of 100 mW. Furthermore, implementing differential privacy-maintained precision with a loss of only 1.2% demonstrates the feasibility of protecting sensitive data without substantially affecting performance. However, precision dropped by 8% in high communication loss scenarios, underlining the importance of stable connectivity for optimal system performance.
format Article
id doaj-art-a0a8bfa080004eb1a05c98161cd20cb2
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a0a8bfa080004eb1a05c98161cd20cb22025-08-20T02:27:45ZengIEEEIEEE Access2169-35362024-01-011217435417437010.1109/ACCESS.2024.350351610758420Optimizing Federated Learning on TinyML Devices for Privacy Protection and Energy Efficiency in IoT NetworksWilliam Villegas-Ch0https://orcid.org/0000-0002-5421-7710Rommel Gutierrez1https://orcid.org/0009-0004-3230-4129Alexandra Maldonado Navarro2Aracely Mera-Navarrete3Escuela de Ingeniería en Ciberseguridad, FICA, Universidad de Las Américas, Quito, EcuadorEscuela de Ingeniería en Ciberseguridad, FICA, Universidad de Las Américas, Quito, EcuadorEscuela de Posgrados, Maestría en Derecho Digital, Universidad de Las Américas, Quito, EcuadorDepartamento de Sistemas, Universidad Internacional del Ecuador, Quito, EcuadorFederated learning is presented as an effective solution to train artificial intelligence models on the Internet of Things networks without centralizing data, thus preserving privacy and minimizing security risks. However, its implementation in low-power devices, such as Tiny Machine Learning, faces significant challenges due to the processing, memory, and unstable connectivity limitations that characterize these environments. This study addresses these issues by developing a federated system optimized for Tiny Machine Learning devices, integrating differential privacy and encryption techniques adapted to their constraints. The methodology employed includes the evaluation of model precision and energy consumption in variable communication scenarios, as well as heterogeneous workloads. The results show that federated learning reduces energy consumption by 33% compared to the centralized approach, reaching an average of 100 mW. Furthermore, implementing differential privacy-maintained precision with a loss of only 1.2% demonstrates the feasibility of protecting sensitive data without substantially affecting performance. However, precision dropped by 8% in high communication loss scenarios, underlining the importance of stable connectivity for optimal system performance.https://ieeexplore.ieee.org/document/10758420/Federated learning in IoTtiny machine learning optimizationprivacy differential techniquesenergy efficiency in edge computing
spellingShingle William Villegas-Ch
Rommel Gutierrez
Alexandra Maldonado Navarro
Aracely Mera-Navarrete
Optimizing Federated Learning on TinyML Devices for Privacy Protection and Energy Efficiency in IoT Networks
IEEE Access
Federated learning in IoT
tiny machine learning optimization
privacy differential techniques
energy efficiency in edge computing
title Optimizing Federated Learning on TinyML Devices for Privacy Protection and Energy Efficiency in IoT Networks
title_full Optimizing Federated Learning on TinyML Devices for Privacy Protection and Energy Efficiency in IoT Networks
title_fullStr Optimizing Federated Learning on TinyML Devices for Privacy Protection and Energy Efficiency in IoT Networks
title_full_unstemmed Optimizing Federated Learning on TinyML Devices for Privacy Protection and Energy Efficiency in IoT Networks
title_short Optimizing Federated Learning on TinyML Devices for Privacy Protection and Energy Efficiency in IoT Networks
title_sort optimizing federated learning on tinyml devices for privacy protection and energy efficiency in iot networks
topic Federated learning in IoT
tiny machine learning optimization
privacy differential techniques
energy efficiency in edge computing
url https://ieeexplore.ieee.org/document/10758420/
work_keys_str_mv AT williamvillegasch optimizingfederatedlearningontinymldevicesforprivacyprotectionandenergyefficiencyiniotnetworks
AT rommelgutierrez optimizingfederatedlearningontinymldevicesforprivacyprotectionandenergyefficiencyiniotnetworks
AT alexandramaldonadonavarro optimizingfederatedlearningontinymldevicesforprivacyprotectionandenergyefficiencyiniotnetworks
AT aracelymeranavarrete optimizingfederatedlearningontinymldevicesforprivacyprotectionandenergyefficiencyiniotnetworks