Abstract
The Industrial Internet of Things (IIoT) promise of autonomous interoperability, solution agility, flexible reconfiguration and repurposing of production chains, foresees that the number of interconnected physical devices in the manufacturing domain will increase drastically, but also that there will be a strong need to interact with edge resources and services to act intelligently and flexibly. This introduces numerous challenges to industrial networked computing environments, which are traditionally quite static and isolated. First, IIoT environments will have to serve a wide range of industrial applications with different Quality-of-Service (QoS) requirements, ranging from traditional, time-sensitive, and reliable closed-loop control systems to event-driven, delay-bounded, or best-effort sensor traffic. Second, in the reconfigurable factories of the future, there will be a strong push towards resource virtualization and disaggregation adding flexibility and support for dynamically composable microservices. This capability demands novel management mechanisms to ensure the end-to-end QoS of co-existing applications, even when new industrial applications are dynamically introduced/removed. Third, several wireless and wired connectivity options will gradually be introduced into production lines, opening new opportunities for QoS specification and control, but also new challenges for heterogeneous QoS-constrained network management. JOULE has the ambition to investigate, model, design, and assess some selected QoS-constrained management mechanisms and strategies for virtualized resources in industrial networked computing environments. This methodological, architectural, modeling and evaluation work will generate best practices, mechanisms, and simple prototypes specialized for reconfigurable I4.0 factories. To this purpose, also considering the project size and timespan, JOULE specifically concentrates on the dynamic (re)allocation/deployment/(re)configuration of compute, storage, and networking resources under per-application requirements on quality, e.g., time and reliability. JOULE will work on the following challenging directions of research: - Unified abstractions and models for distributed heterogeneous virtualized resources, allowing us to express and map high-level QoS to actionable low-level management decisions - Innovative algorithms and mechanisms for dynamic end-to-end reallocation and reconfiguration of virtualized (containerized) resources able to consider the above requirements - Distributed QoS-constrained orchestration of industrial support/service components that efficiently use compute, storage, and networking virtualized resources - Qualitative assessment and minimal viable demonstration of the proposed mechanisms/strategies in a “Shared and Distributed Manufacturing” scenario entailing dynamically reconfigurable production lines.
Dettagli del progetto
Responsabile scientifico: Paolo Bellavista
Strutture Unibo coinvolte:
Dipartimento di Informatica - Scienza e Ingegneria
Coordinatore:
ALMA MATER STUDIORUM - Università di Bologna(Italy)
Contributo totale di progetto: Euro (EUR) 228.130,00
Contributo totale Unibo: Euro (EUR) 82.104,00
Durata del progetto in mesi: 24
Data di inizio
28/09/2023
Data di fine:
28/09/2025
