Answers are grounded in this paper and cite their sources.
Introduction The compute continuum, together with the high-speed and reliable connectivity provided by advanced communication technologies such as 5G or beyond 5G (B5G) networks, enables the development of new types of applications and services. However, deciding when application components should be re-instantiated and selecting the most appropriate destination node according to dynamic execution conditions remains a challenge. Although artificial intelligence (AI), among other techniques, has emerged as a promising approach to address these challenges, the integration and evaluation of such orchestrators remain complex due to the lack of modular and standardized architectures. Methods In this work, we present FABRIC, an orchestration platform that aims to evolve current 5G networks by enabling the re-instantiation of computational tasks whenever required through continuous computing and advanced task orchestration across distributed resources, all this whilst being aligned with current 3GPP and ETSI standards. This architecture bridges the gap between distributed computing paradigms and modern mobile network architectures, anticipating the computational and operational demands of next-generation mobile networks thanks to its standards-based nature. This modular design facilitates the implementation of sophisticated re-instantiation strategies while promoting interoperability and extensibility, fostering the adoption of more advanced orchestration mechanisms for future compute continuum environments supported by 5G/B5G networks. Results FABRIC is assessed with two use case scenarios, one with a CPU-intensive task and another one re-instantiating an application with user traffic. Discussion The results demonstrate that FABRIC supports interoperable service re-instantiation across the compute continuum, while facilitating service orchestration adapted to the requirements of each use case.
No takes yet. Share an insight, caveat, or question.
Nieto et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: