NexusForum.EU Wiki

MLSysOps: Difference between revisions

VisualWikitext
Created page with "==EU Project short name::MLSysOps== ===EU Project full name::Machine Learning for Autonomic System Operation in the Heterogeneous Edge-Cloud Continuum=== '''Full project details (EU Research results portal):''' CORDIS URL::https://cordis.europa.eu/project/id/101092912 === '''Project description:''' === MLSysOps will achieve substantial research contributions in the realm of AI-based system adaptation across the cloud-edge continuum by introducing advanced me..."
 
No edit summary
 
(One intermediate revision by the same user not shown)
Line 10: Line 10:
'''EU Programme:'''
'''EU Programme:'''
[[Programme::Horizon Europe]]
[[Programme::Horizon Europe]]
[[ItemType::EU Project]]
'''Project publications:'''
{{#ask:
[[Category:Publications]]
[[EU Project::MLSysOps]]
| ?EU Project = EU Project
| ?Has Title#- = Title
| ?Has Category#- = Category
| ?Has Type#- = Type
| ?Has Year#- = Year
| ?Has DOI = DOI
| format=datatables
| limit=1000
| mainlabel=-
| searchable=yes
| column filters=select
| noajax=yes
}}

Latest revision as of 13:07, 8 May 2026

MLSysOps

Machine Learning for Autonomic System Operation in the Heterogeneous Edge-Cloud Continuum

Full project details (EU Research results portal): https://cordis.europa.eu/project/id/101092912

Project description:

MLSysOps will achieve substantial research contributions in the realm of AI-based system adaptation across the cloud-edge continuum by introducing advanced methods and tools to enable optimal system management and application deployment. MLSysOps will design, implement and evaluate a complete framework for autonomic end-to-end system management across the full cloud-edge continuum. MLSysOps will employ a hierarchical agent-based AI architecture to interface with the underlying resource management and application deployment/orchestration mechanisms of the continuum. Adaptivity will be achieved through continual ML model learning in conjunction with intelligent retraining concurrently to application execution, while openness and extensibility will be supported through explainable ML methods and an API for pluggable ML models. Flexible/efficient application execution on heterogeneous infrastructures and nodes will be enabled through innovative portable container-based technology. Energy efficiency, performance, low latency, efficient, resilient and trusted tier-less storage, cross-layer orchestration including resource-constrained devices, resilience to imperfections of physical networks, trust and security, are key elements of MLSysOps addressed using ML models. The framework architecture disassociates management from control and seamlessly interfaces with popular control frameworks for different layers of the continuum. The framework will be evaluated using research testbeds as well as two real-world application-specific testbeds in the domain of smart cities and smart agriculture, which will also be used to collect the system-level data necessary to train and validate the ML models, while realistic system simulators will be used to conduct scale-out experiments. The MLSysOps consortium is a balanced blend of academic/research and industry/SME partners, bringing together the necessary scientific and technological skills to ensure successful implementation and impact.

EuroVoc IDs: /natural sciences/computer and information sciences/internet/internet of things

EU Programme: Horizon Europe

EU Project

Project publications:

EU ProjectHas TitleHas CategoryHas TypeHas YearHas DOI
MLSysOpsCooper: A Lightweight Event Recording and Visualization Framework for Data Center SimulationsArtificial Intelligence and Machine Learning SystemsConference proceedings2025https://doi.org/10.1007/978-3-032-13744-9 2
MLSysOpsSplit Learning Based GAN Training for Non-IID Federated LearningArtificial Intelligence and Machine Learning SystemsConference proceedings2025https://doi.org/10.1007/978-3-032-13744-9 5
MLSysOpsBenefits of Agent-Oriented Transitioning from Monolithic To Service-Based ArchitecturesArtificial Intelligence and Machine Learning SystemsConference proceedings2024https://doi.org/10.1109/INISTA62901.2024.10683829
MLSysOpsPer Priority Data Rate Measurement in Data PlaneArtificial Intelligence and Machine Learning SystemsConference proceedings2023https://doi.org/10.1145/3630047.3630199
MLSysOpsAIRISC - A mmWave Angle-Insensitive Reconfigurable Intelligent Surface Communication SystemArtificial Intelligence and Machine Learning SystemsConference proceedings2023https://doi.org/10.5555/3639940.3639961
MLSysOpsEdge-cloud continuum driven industry 4.0Artificial Intelligence and Machine Learning SystemsConference proceedings2025https://doi.org/10.1016/J.PROCS.2025.01.318
MLSysOpsShould I Stay or Should I Go: A Learning Approach for Drone-based Sensing ApplicationsArtificial Intelligence and Machine Learning SystemsConference proceedings2024https://doi.org/10.48550/ARXIV.2409.04764
MLSysOpsIdentifying and Exploiting a Denial-Of-Service Vulnerability in the NGAP Protocol in 5G NetworksArtificial Intelligence and Machine Learning SystemsConference proceedings2025https://doi.org/10.1109/EUCNC/6GSUMMIT63408.2025.11036893
MLSysOpsEnabling Cloud-native IoT device managementArtificial Intelligence and Machine Learning SystemsConference proceedings2024https://doi.org/10.1145/3642975.3678967
MLSysOpsIoTNetEMU - A Framework to Emulate and Test IoT ApplicationsArtificial Intelligence and Machine Learning SystemsConference proceedings2023https://doi.org/10.1145/3616391.3622774
MLSysOpsSandboxing Functions For Efficient and Secure Multi-tenant Serverless DeploymentsArtificial Intelligence and Machine Learning SystemsConference proceedings2024https://doi.org/10.5281/ZENODO.11545513
MLSysOpsDevelopment and Validation of a Proximity-based Wearable Computing Testbed for Community-oriented Wearable SystemsArtificial Intelligence and Machine Learning SystemsConference proceedings2024https://doi.org/10.48550/ARXIV.2406.02311
MLSysOpsDPUConfig: Optimizing ML Inference in FPGAs Using Reinforcement LearningArtificial Intelligence and Machine Learning SystemsConference proceedings2026https://doi.org/10.48550/ARXIV.2602.12847
MLSysOpsTowards an Edge Intelligence-based Traffic Monitoring SystemArtificial Intelligence and Machine Learning SystemsConference proceedings2023https://doi.org/10.1109/SMC53992.2023.10393907
MLSysOpsFrom Sound to Sight: Audio-Visual Fusion and Deep Learning for Drone DetectionArtificial Intelligence and Machine Learning SystemsConference proceedings2024https://doi.org/10.1145/3643833.3656133
MLSysOpsUsing Machine Learning to Take Stay-or-Go Decisions in Data-driven Drone MissionsArtificial Intelligence and Machine Learning SystemsConference proceedings2025https://doi.org/10.48550/ARXIV.2512.04773
MLSysOpsTMModel: Modeling Texture Memory and Mobile GPU Performance to Accelerate DNN ComputationsArtificial Intelligence and Machine Learning SystemsConference proceedings2025https://doi.org/10.1145/3721145.3725774
MLSysOpsSupporting the Adaptive Deployment of Modular Applications in Cloud-Edge-Mobile SystemsArtificial Intelligence and Machine Learning SystemsConference proceedings2023https://doi.org/10.5555/3639940.3639966
MLSysOpsA Generative AI-Driven Architecture for Intelligent Transportation SystemsArtificial Intelligence and Machine Learning SystemsConference proceedings2024https://doi.org/10.1109/WF-IOT62078.2024.10811280
MLSysOpsTinyKubeML: Orchestrating TinyML Models on Far-Edge ClustersArtificial Intelligence and Machine Learning SystemsConference proceedings2025https://doi.org/10.5281/ZENODO.18494389
MLSysOpsDisjunctive Multi-Level Digital Forgetting SchemeArtificial Intelligence and Machine Learning SystemsConference proceedings2024https://doi.org/10.1145/3605098.3635904
Retrieved from "https://wiki.eucloudedgeiot.eu/index.php?title=MLSysOps&oldid=3727"