MLSysOps

MLSysOps (Machine Learning for Autonomic System Operation in the Heterogeneous Edge-Cloud Continuum) aims to enable the autonomous, efficient, and adaptive management of end-to-end systems in the heterogeneous and dynamic edge-cloud continuum through the use of AI models.

The MLSysOps project will introduce an AI-driven control and management framework that interfaces with off-the-shelf management mechanisms and employs a hierarchical, distributed, explainable, and evolving AI architecture for the operation of autonomic systems. MLSysOps will demonstrate its efficacy through two well-defined use cases in precision agriculture and smart cities, utilising cloud, smart, and deep-edge infrastructures. The use cases correspond to dynamic, highly impactful applications with widely heterogeneous demands.

Key elements of MLSysOps, addressed using ML models, include energy efficiency and utilisation of green energy, performance, low latency, efficient and trusted tierless storage, cross-layer orchestration including resource-constrained devices, resilience to imperfections in physical networks, trust, and security.

Ubiwhere is responsible for the energy efficiency study in the Smart City application use case, which aims to make streets and pavements safer for pedestrians by analysing how demand patterns change, identifying emergencies, and providing faster responses, as well as conducting complex analyses.

This project has received funding from the European Union.