Embedded federated learning over a LoRa mesh network

In on-device training of machine learning models on microcontrollers a neural network is trained on the device. A specific approach for collaborative on-device training is federated learning. In this paper, we propose embedded federated learning on microcontroller boards using the communication capa...

Descripción completa

Detalles Bibliográficos
Autores: Llisterri i Giménez, Nil|||0000-0003-1896-2868, Miquel Solé, Joan|||0000-0003-3737-376X, Freitag, Fèlix|||0000-0001-5438-479X
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/393829
Acceso en línea:https://hdl.handle.net/2117/393829
https://dx.doi.org/10.1016/j.pmcj.2023.101819
Access Level:acceso abierto
Palabra clave:Machine learning
Internet of things
Microcontrollers
Embedded machine learning
Federated learning
LoRa
IoT
Aprenentatge automàtic
Internet de les coses
Microcontroladors
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors
Descripción
Sumario:In on-device training of machine learning models on microcontrollers a neural network is trained on the device. A specific approach for collaborative on-device training is federated learning. In this paper, we propose embedded federated learning on microcontroller boards using the communication capacity of a LoRa mesh network. We apply a dual board design: The machine learning application that contains a neural network is trained for a keyword spotting task on the Arduino Portenta H7. For the networking of the federated learning process, the Portenta is connected to a TTGO LORA32 board that operates as a router within a LoRa mesh network. We experiment the federated learning application on the LoRa mesh network and analyze the network, system, and application level performance. The results from our experimentation suggest the feasibility of the proposed system and exemplify an implementation of a distributed application with re-trainable compute nodes, interconnected over LoRa, entirely deployed at the tiny edge.