Edge-Cloud Computing

Area Overview

Edge-Cloud Computing represents a paradigm shift—bringing computation, storage, and intelligence closer to where data is generated, enabling faster, more efficient, and context-aware digital services.

Digital systems are increasingly data-driven and latency-sensitive, as such the traditional model of centralised cloud computing is no longer sufficient. A distributed approach is required that enables the next generation of applications—from autonomous systems and smart cities to real-time digital twins and immersive experiences.

The convergence of edge and cloud computing is a foundational capability for enabling responsive, scalable, and secure digital ecosystems. Research in this domain is critical to:

Reduce latency and bandwidth demands for real-time applications

Enhance data privacy and sovereignty by processing sensitive data locally

Improve resilience and continuity in decentralized and mission-critical environments

Support AI at the edge, enabling intelligent decision-making closer to the source

Enable the twin transition, by supporting both digital innovation and sustainable infrastructure

Our Focus

As systems become more distributed and autonomous, understanding how to orchestrate, secure, and optimise edge-cloud architectures is key to unlocking future capabilities across sectors. Nimbus envisions a future where edge-cloud systems work seamlessly together, enabling intelligent, secure and trusted context-aware services. This is enabled through research in the following areas:

Distributed Systems Architectures: enabling interoperable, heterogeneous infrastructure that is scalable and resilient, integrating across OT, IT, IoT and cloud networks and platforms.

Security, Privacy & Trusted Distributed Environments: Investigating the application of Zero Trust Architectures across edge-cloud continuum.

Dynamic Resource Allocation and 3C Networks: AI-driven workload distribution across edge and cloud layers providing real-time adaption under constrained conditions (e.g. resource availability, security, energy).

Data Distribution, AI and ML at the edge: Development of distributed data spaces for privacy preserving data processing (e.g. federated learning); lightweight, efficient models for deployment in edge environments as well as support tools for distributed ML workflows

Edge-cloud Computing