Go Back
Smart Deployment Solution for PNRR MUSA services in Edge-Cloud Continuum

Smart Deployment Solution for PNRR MUSA services in Edge-Cloud Continuum

Claudio A. Ardagna, Marco Anisetti
Deployment of Big Data and AI-based services in modern distributed systems, at the basis of the innovation ecosystem developed as part of the PNRRR project MUSA
10 December 2023
VIDEO

Abstract

Modern data processing applications are increasingly designed as a composition of micro and nano services and are progressively adopted to handle critical scenarios where advanced Quality of Services (QoS) such as low latency, security, and privacy are fundamental. Nowadays, there is a clear trend in adopting composition execution plans that span from the far edge to the cloud. With the advent of 5G, this edge cloud continuum is enriched with edge computation facilities provided by telco operators improving its capabilities to support advanced QoS. Actual deployment solutions for compositions focus mainly on resource allocation (i.e., CPU, memory, and storage), falling short of addressing advanced QoS and complex Edge Cloud continuum infrastructures.

Project Multilayered Urban Sustainability Action (MUSA), an innovation ecosystem funded by PNRR in Italy, under its Spoke 2 aims to the design, implement, and deploy a highly innovative, secure digital platform for Big Data collection, sharing, and analysis suitable for both clinical practices, health services, and life science applications. The MUSA digital platform is based on an advanced Edge-Cloud Continuum involving 5G network communications and edge nodes. It supports the creation and smart deployment of advanced data processing pipelines built on AI/ML services and Big Data analytics, which continuously support critical QoS requirements.

This talk presents the MUSA QoS-aware deployment solution for Edge-Cloud Continuum. The proposed solution compares the QoS requirements with the capabilities of a given edge cloud continuum to find, generate, and execute suitable deployment recipes. It is also instrumented by assurance controls to continuously verify the requested QoS. The talk finally presents the next steps and activities along two main axes: smart deployer for 5G and Advanced testing infrastructure.

Speakers

  • Claudio A. Ardagna
    Università degli Studi di Milano
    HOMEPAGE

    Claudio A. Ardagna is Full Professor with the Università degli Studi di Milano, the Director of the CINI National Lab on Data Science, and co-founder of Moon Cloud srl. His research interests are in the areas of cloud-edge security and assurance, distributed system certification, machine learning, and data science, where he published more than 150 contributions in international journals, conference/workshop proceedings, and chapters in international books. He is the winner of the ERCIM (European Research Consortium for Informatics and Mathematics) WG STM 2009 Award for the Best Ph.D. Thesis on Security and Trust Management. He has been visiting professor at Université Jean Moulin Lyon 3 and visiting researcher at Beijing University of Posts and Telecommunications, Khalifa University, George Mason University. He is member of the Steering Committee of IEEE Transactions on Cloud Computing, member of the editorial board of the IEEE Transactions on Cloud Computing and IEEE Transactions on Services Computing, and secretary of the IEEE Technical Committee on Services Computing. He is General Chair for IEEE ICWS 2024.

  • Marco Anisetti
    Università degli Studi di Milano
    HOMEPAGE

    Marco Anisetti is Full Professor at the Università degli Studi di Milano. His research interests are in the area of computational intelligence, and its application to the design and evaluation of complex systems. He has been investigating innovative solutions in the area of cloud security assurance evaluation. In this area he defined a new scheme for continuous and incremental cloud security certification, based on distributed assurance evaluation architecture.