Orchestrating networked machine learning applications using Autosteer

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Wen, Zhenyu
• dc.contributor.author Hu, Haozhen
• dc.contributor.author Yang, Renyu
• dc.contributor.author Qian, Bian
• dc.contributor.author Sham, Ringo W.H.
• dc.contributor.author Rui, Sun
• dc.contributor.author Xu, Jie
• dc.contributor.author Patel, Pankesh
• dc.contributor.author Rana, Omer
• dc.contributor.author Dustdar, Schahram
• dc.contributor.author Ranjan, Rajiv
• dc.date.accessioned 2023-07-26T07:14:10Z
• dc.date.issued 2022
• dc.description.abstract A platform for orchestrating networked machine learning (ML) applications over distributed environments is described. ML applications are transformed into automated pipelines that manage the whole application lifecycle and production-grade implementations are automatically constructed. We present AUTOSTEER, a software platform that can deploy ML applications on various hardware resources—interconnected using heterogeneous network resources—across cloud and edge devices. Device placement optimization and model adaptation are used as control actions to support application requirements and maximize the performance of ML model execution over heterogeneous computing resources. The performance of deployed applications is continually monitored at runtime to overcome performance degradation due to incorrect application parameter settings or model decay. Three real-world applications are used to demonstrate how AUTOSTEER can support application deployment and runtime performance guarantees.
• dc.format.mimetype application/pdf
• dc.identifier.citation Wen Z, Hu H, Yang R, Qian B, Sham RWH, Sun R, Xu J, Patel P, Rana O, Dustdar S, Ranjan R. Orchestrating networked machine learning applications using Autosteer. IEEE Internet Comput. 2022;26(6):51-8. DOI: 10.1109/MIC.2022.3180907
• dc.identifier.doi http://dx.doi.org/10.1109/MIC.2022.3180907
• dc.identifier.issn 1089-7801
• dc.identifier.uri http://hdl.handle.net/10230/57669
• dc.language.iso eng
• dc.publisher Institute of Electrical and Electronics Engineers (IEEE)
• dc.relation.ispartof IEEE Internet Computing. 2022;26(6):51-8.
• dc.rights © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/MIC.2022.3180907
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Performance evaluation
• dc.subject.keyword Degradation
• dc.subject.keyword Training data
• dc.subject.keyword Adaptation models
• dc.subject.keyword Cloud computing
• dc.subject.keyword Runtime
• dc.subject.keyword Computational modeling
• dc.title Orchestrating networked machine learning applications using Autosteer
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/acceptedVersion