Architecture for Enabling Edge Inference via Model Transfer from Cloud Domain in a Kubernetes Environment
Publiceringsår
2021
Upphovspersoner
Pääkkönen, Pekka; Pakkala, Daniel; Kiljander, Jussi; Sarala, Roope
Abstrakt
The current approaches for energy consumption optimisation in buildings are mainly reactive or focus on scheduling of daily/weekly operation modes in heating. Machine Learning (ML)-based advanced control methods have been demonstrated to improve energy efficiency when compared to these traditional methods. However, placing of ML-based models close to the buildings is not straightforward. Firstly, edge-devices typically have lower capabilities in terms of processing power, memory, and storage, which may limit execution of ML-based inference at the edge. Secondly, associated building information should be kept private. Thirdly, network access may be limited for serving a large number of edge devices. The contribution of this paper is an architecture, which enables training of ML-based models for energy consumption prediction in private cloud domain, and transfer of the models to edge nodes for prediction in Kubernetes environment. Additionally, predictors at the edge nodes can be automatically updated without interrupting operation. Performance results with sensor-based devices (Raspberry Pi 4 and Jetson Nano) indicated that a satisfactory prediction latency (~7–9 s) can be achieved within the research context. However, model switching led to an increase in prediction latency (~9–13 s). Partial evaluation of a Reference Architecture for edge computing systems, which was used as a starting point for architecture design, may be considered as an additional contribution of the paper.
Visa merOrganisationer och upphovspersoner
Publikationstyp
Publikationsform
Artikel
Moderpublikationens typ
Tidning
Artikelstyp
En originalartikel
Målgrupp
VetenskapligKollegialt utvärderad
Kollegialt utvärderadUKM:s publikationstyp
A1 Originalartikel i en vetenskaplig tidskriftPublikationskanalens uppgifter
Öppen tillgång
Öppen tillgänglighet i förläggarens tjänst
Ja
Öppen tillgång till publikationskanalen
Helt öppen publikationskanal
Licens för förläggarens version
CC BY
Parallellsparad
Nej
Publiceringsavgift för öppen tillgång €
829
Betalningsår för den öppen tillgång publiceringsavgiften
2021
Övriga uppgifter
Vetenskapsområden
Data- och informationsvetenskap; El-, automations- och telekommunikationsteknik, elektronik
Nyckelord
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Språk
engelska
Internationell sampublikation
Nej
Sampublikation med ett företag
Nej
DOI
10.3390/fi13010005
Publikationen ingår i undervisnings- och kulturministeriets datainsamling
Ja