Survey and enhancements on deploying LSTM recurrent neural networks on embedded systems - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Survey and enhancements on deploying LSTM recurrent neural networks on embedded systems

Résumé

The real implementation of a recurrent neural network (RNN) in a low complexity IoT device is evaluated in order to predict the time series of power consumption in tertiary buildings. The RNN type long short-term memory (LSTM) algorithm is adapted for a 32-bit microcontroller unit (MCU) and the backpropagation (BP) algorithm is implemented in-house. We therefore demonstrate that Intelligent IoT (IIoT) devices, such as the Espressif ESP32 MCU, not only implement neural networks (NNs), but also learn on their own. The resulting IIoT architecture has been proven to operate efficiently and compared to the traditional computer-based learning platform. The selected results confirm that stand-alone IoT devices are a truly efficient solution that adds flexibility to the architecture, reduces storage and computation costs, and is more energy-friendly. As a conclusion, it is practically more efficient to exploit low-power and processing-time IIoT for our prediction use case rather than relying on server based distributed systems.
Fichier principal
Vignette du fichier
IA___Embarqué.pdf (166.21 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04173980 , version 1 (01-08-2023)

Identifiants

Citer

Ghalid Abib, Florian Castel, Nissrine Satouri, Hossam Afifi, Adel Mounir Said. Survey and enhancements on deploying LSTM recurrent neural networks on embedded systems. ICC 2023: IEEE International Conference on Communications, IEEE, May 2023, Rome, Italy. pp.2034, ⟨10.1109/ICC45041.2023.10278766⟩. ⟨hal-04173980⟩
71 Consultations
45 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More