Implementing a CNN in FPGA programmable logic for NILM application
Authors
Tapiador Luque, Miguel; Diego Otón, Laura De; Hernández Alonso, Álvaro; Nieto Capuchino, RubénIdentifiers
Permanent link (URI): http://hdl.handle.net/10017/60339DOI: 10.1109/DCIS58620.2023.10335989
ISBN: 979-8-3503-0385-8
Publisher
IEEE
Date
2023-12-11Embargo end date
2024-12-11Funders
Agencia Estatal de Investigación
Bibliographic citation
Tapiador Luque, M., Diego Otón, L., Hernández Alonso, A. & Nieto Capuchino, R. 2023, “Implementing a CNN in FPGA programmable logic for NILM application”, in 2023 38th Conference on Design of Circuits and Integrated Systems (DCIS), Málaga, Spain, pp 1-6.
Keywords
Non-Intrusive Load Monitoring (NILM)
System-on-Chip (SoC)
Field-Programmable Gate Array (FPGA)
Artificial Neural Networks (ANN)
Description / Notes
2023 38th Conference on Design of Circuits and Integrated Systems (DCIS), 15-17 November 2023, Málaga, Spain.
Project
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-105470RA-C33/ES/MEJORANDO Y FOMENTANDO LA VIDA ACTIVA Y BIENESTAR DE LAS PERSONAS CON DEMENCIA Y DETERIORO COGNITIVO LEVE MEDIANTE EL USO DE TECNICAS DE LOCALIZACION/
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica, Técnica y de Innovación 2021-2023/TED2021-131773B-100
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-115995RB-I00/ES/TECNICAS DE APRENDIZAJE PARA RESOLVER LA RECONSTRUCCION Y REGISTRO DEFORMABLES APLICADOS A IMAGENES DE LAPAROSCOPIA/
Document type
info:eu-repo/semantics/bookPart
Version
info:eu-repo/semantics/acceptedVersion
Publisher's version
https://doi.org/10.1109/DCIS58620.2023.10335989Rights
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
© 2023 IEEE
Access rights
info:eu-repo/semantics/embargoedAccess
Abstract
Non-Intrusive Load Monitoring (NILM) techniques are gaining popularity in the field of energy savings. Generally implemented through the use of smart meters, the main challenge with these devices is that they operate at very low sampling rates. To address this issue, FPGA-based systems have been proposed to capture instantaneous currents and voltages at higher sampling frequencies in the kHz range. However, the limitation of these architectures lies in the fact that the acquired windows are often transmitted upstream to the cloud for the application of load classification algorithms based on machine learning, relying on high-bandwidth communications available onsite. This work proposes an alternative approach by implementing the classification algorithms in the same acquisition and processing system, by using custom convolutional neural networks on mid-range FPGA devices. Brevitas and FINN frameworks are used for the quantization-aware training, as well as for the generation of a peripheral that may be integrated into any FPGA-based SoC (System-on-Chip) architecture. The proposed approach allows the whole processing involved in NILM techniques to be integrated into a single embedded system. Preliminary experimental results demonstrate the effectiveness of the proposed approach.
Files in this item
Files | Size | Format |
|
---|---|---|---|
Implementing_Tapiador_DCIS_2023.pdf | 1.158Mb |
|
Files | Size | Format |
|
---|---|---|---|
Implementing_Tapiador_DCIS_2023.pdf | 1.158Mb |
|