<div class="csl-bib-body">
<div class="csl-entry">Sedlak, B., Casamayor Pujol, V., Donta, P. K., & Dustdar, S. (2023). <i>Active Inference on the Edge : A Design Study</i>. arXiv. https://doi.org/10.34726/5939</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/195912
-
dc.identifier.uri
https://doi.org/10.34726/5939
-
dc.description.abstract
Machine Learning (ML) is a common tool to interpret and predict the behavior of distributed computing systems, e.g., to optimize the task distribution between devices. As more and more data is created by Internet of Things (IoT) devices, data processing and ML training are carried out by edge devices in close proximity. To ensure Quality of Service (QoS) throughout these operations, systems are supervised and dynamically adapted with the help of ML. However, as long as ML models are not retrained, they fail to capture gradual shifts in the variable distribution, leading to an inaccurate view of the system state. Moreover, as the prediction accuracy decreases, the reporting device should actively resolve uncertainties to improve the model's precision. Such a level of self-determination could be provided by Active Inference (ACI) -- a concept from neuroscience that describes how the brain constantly predicts and evaluates sensory information to decrease long-term surprise. We encompassed these concepts in a single action-perception cycle, which we implemented for distributed agents in a smart manufacturing use case. As a result, we showed how our ACI agent was able to quickly and traceably solve an optimization problem while fulfilling QoS requirements.
en
dc.description.sponsorship
European Commission
-
dc.language.iso
en
-
dc.rights.uri
http://creativecommons.org/licenses/by-nc-nd/4.0/
-
dc.subject
Active Inference
en
dc.subject
Machine Learning
en
dc.subject
Edge Intelligence
en
dc.subject
Service Level Objectives
en
dc.subject
Markov Blanket
en
dc.title
Active Inference on the Edge : A Design Study
en
dc.type
Preprint
en
dc.type
Preprint
de
dc.rights.license
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
en
dc.rights.license
Creative Commons Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International
de
dc.identifier.doi
10.34726/5939
-
dc.identifier.arxiv
2311.10607
-
dc.relation.grantno
101070186
-
tuw.project.title
Trustworthy, Energy-Aware federated DAta Lakes along the Computing Continuum
-
tuw.researchTopic.id
I4
-
tuw.researchTopic.name
Information Systems Engineering
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E194-02 - Forschungsbereich Distributed Systems
-
tuw.publisher.doi
10.48550/arXiv.2311.10607
-
dc.description.numberOfPages
6
-
tuw.author.orcid
0009-0001-2365-8265
-
tuw.author.orcid
0000-0003-2830-8368
-
tuw.author.orcid
0000-0002-8233-6071
-
tuw.author.orcid
0000-0001-6872-8821
-
dc.rights.identifier
CC BY-NC-ND 4.0
en
dc.rights.identifier
CC BY-NC-ND 4.0
de
tuw.publisher.server
arXiv
-
wb.sciencebranch
Informatik
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.value
100
-
item.openaccessfulltext
Open Access
-
item.fulltext
with Fulltext
-
item.languageiso639-1
en
-
item.openairecristype
http://purl.org/coar/resource_type/c_816b
-
item.openairetype
preprint
-
item.mimetype
application/pdf
-
item.grantfulltext
open
-
item.cerifentitytype
Publications
-
crisitem.project.funder
European Commission
-
crisitem.project.grantno
101070186
-
crisitem.author.dept
E194-02 - Forschungsbereich Distributed Systems
-
crisitem.author.dept
E194-02 - Forschungsbereich Distributed Systems
-
crisitem.author.dept
E194-02 - Forschungsbereich Distributed Systems
-
crisitem.author.dept
E194-02 - Forschungsbereich Distributed Systems
-
crisitem.author.orcid
0009-0001-2365-8265
-
crisitem.author.orcid
0000-0003-2830-8368
-
crisitem.author.orcid
0000-0002-8233-6071
-
crisitem.author.orcid
0000-0001-6872-8821
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering