MLSysOps - Machine Learning for Autonomic System Operation in the Heterogeneous Edge-Cloud Continuum
The main objective of MLSysOps is to design, implement and evaluate a complete AI-controlled 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. Energy efficiency and utilization of green energy, performance, low latency, efficient, 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.
Dynamic adaptivity of system configuration 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. 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.
MLSysOps is not only fully aligned with current trends towards the expansion of cloud infrastructure towards integration with smart and deep edge resources, but it also achieves 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. 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.
NEWS
Presentation at ACSAC
Ildi Alla et. al. of INRIA will be presenting a paper titled "Robust Device Authentication…
4th Plenary Meeting
On Oct 24 and 25, Ubiwhere's headquarters welcomed the members of the MLSysOps Project consortium…
Invited talk at the 5G/6G Open Industry Day
Valeria Loscri of INRIA gave a talk on "Security Aspects in IoT-Edge-Cloud Continuum" at the…
MLSysOps @ SuperScienceMe 2024 – EU Researcher Night
MLSysOps Project was present at the "EU Corner" of the SuperScienceMe 2024 - EU Researcher…
Invited talk at TALK.CYBERCNI.fr
Valeria Loscri of INRIA was invited to TALK.CYBERCNI.fr. Watch here [linkedin] her talk on "Security…
Invited talk at the 2nd AIoTwin Summer School
Spyros Lalis of UTH gave a talk about "Elevating Drones as first-class citizens in the…
MLSysOps @ EUCEI’s Open Continuum Final Conference
MLSysOps is participating in EUCEI’s Open Continuum Final Conference which focuses on the value of…
3rd Plenary Meeting
The 3rd MLSysOps plenary meeting took place in Dublin this month. Thank you to UCD…
Tutorial Presentation on IoT-Edge-Cloud-Continuum Security Issues
Valeria Loscrì of Inria, FR, gave a tutorial presentation on IoT-Edge-Cloud-Continuum Security Issues at the…
Talk at OpenInfra Days Europe 2024
Anastassios Nanos of Nubis was invited to talk at OpenInfra Days Europe 2024. His talk,…
Presentation at WiSec ’24
Ildi Alla et al presented a paper titled "From Sound to Sight: Audio-Visual Fusion and…
MLSysOps-related visit to IBM Research Ireland
Members of the decentralised AI systems lab of UCD (Dimitris Chatzopoulos, Joana Tirana, John Byabazaire,…
Presentation at IEEE INFOCOM 2024
Joana Tirana (UCD) and Dimitris Chatzopoulos (UCD), in collaboration with Dimitra Tsigkari and George Iosifidis…
Presentation at S3
Nikita Yadav et al presented a paper titled "Orbital Shield: Rethinking Satellite Security in the…
New publication in SAC 24
TUD's paper titled "Disjunctive Multi-Level Digital Forgetting Scheme" has been published in the proceedings of…