Orfeon: an AIOps framework for the goal-driven operationalization of distributed analytical pipelines

dc.contributor.authorDíaz de Arcaya Serrano, Josu
dc.contributor.authorTorre Bastida, Ana Isabel
dc.contributor.authorMiñón Jiménez, Raúl
dc.contributor.authorAlmeida, Aitor
dc.date.accessioned2024-11-07T10:24:47Z
dc.date.available2024-11-07T10:24:47Z
dc.date.issued2023-03
dc.date.updated2024-11-07T10:24:47Z
dc.description.abstractThe use of Artificial Intelligence solutions keeps raising in the business domain. However, this adoption has not brought the expected results to companies so far. There are several reasons that make Artificial Intelligence solutions particularly complicated to adopt by businesses, such as the knowledge gap between the data science and operations teams. In this paper, we tackle the operationalization of distributed analytical pipelines in heterogeneous production environments, which span across different computational layers. In particular, we present a system called Orfeon, which can leverage different objectives and yields an optimized deployment for these pipelines. In addition, we offer the mathematical formulation of the problem alongside the objectives in hand (i.e. resilience, performance, and cost). Next, we propose a scenario utilizing cloud and edge infrastructural devices, in which we demonstrate how the system can optimize these objectives, without incurring scalability issues in terms of time nor memory. Finally, we compare the usefulness of Orfeon with a variety of tools in the field of machine learning operationalization and conclude that it is able to outperform these tools under the analyzed criteria, making it an appropriate system for the operationalization of machine learning pipelines.en
dc.description.sponsorshipThe work presented in this research was partially supported by the SPRI–Basque Government through their ELKARTEK program (B-Ind5 g, ref.KK-2021/00026). Aitor Almeida's participation was supported by the Spanish Ministry of Science, Innovation and Universities through their “Retos Investigación” program (FuturAALEgo, ref.RTI2018-101045-A-C22)en
dc.identifier.citationDíaz-de-Arcaya, J., Torre-Bastida, A. I., Miñón, R., & Almeida, A. (2023). Orfeon: An AIOps framework for the goal-driven operationalization of distributed analytical pipelines. Future Generation Computer Systems, 140, 18-35. https://doi.org/10.1016/J.FUTURE.2022.10.008
dc.identifier.doi10.1016/J.FUTURE.2022.10.008
dc.identifier.issn0167-739X
dc.identifier.urihttp://hdl.handle.net/20.500.14454/1686
dc.language.isoeng
dc.publisherElsevier B.V.
dc.rights© 2022 Elsevier B.V.
dc.subject.otherAIOps
dc.subject.otherAnalytical pipelines
dc.subject.otherEdge computing
dc.subject.otherMachine learning operationalization
dc.subject.otherMLOps
dc.titleOrfeon: an AIOps framework for the goal-driven operationalization of distributed analytical pipelinesen
dc.typejournal article
dcterms.accessRightsmetadata only access
oaire.citation.endPage35
oaire.citation.startPage18
oaire.citation.titleFuture Generation Computer Systems
oaire.citation.volume140
Ficheros en el ítem
Colecciones