FRACTAL
Cognitive edge node for edge computing – design and build a reliable computing node that creates a cognitive edge compliant with industry standards. This node acts as a scalable building block for IoT systems from low‑power to high‑performance edge nodes. Its cognitive skills come from an internal and external architecture capable of forecasting its internal state and the surrounding world, enabling it to learn and improve performance under uncertainty. When these nodes are integrated into a fractal network, they confer autonomy, adaptability and emergent functions to the edge and facilitate seamless interaction between the physical world and the cloud
Description
FRACTAL addresses the challenge of industrial edge computing, which requires time‑predictability, dependability, energy‑efficiency and security. The project aims to create an open‑safe‑reliable and power‑efficient cognitive edge node to serve as a building block for scalable IoT from smart low‑energy systems to high‑performance edge nodes. Cognitivity is achieved via AI‑enabled architectures that allow the node to adapt to changes in real time and improve its performance despite environmental uncertainty. These nodes are integrated into a fractal edge network that delivers safety, adaptability and emergent functionality, bridging the physical world and the cloud.
Focus points/areas
-
Open, safe, low-power cognitive edge nodes with AI-driven adaptation in a fractal edge network.
Methodology
FRACTAL adopts a disruptive, cross‑layer methodology. The project uses cutting‑edge microelectronics, high‑performance processors and AI techniques to build a modular, open reference architecture for cognitive edge computing. A modular open reference architecture allows components to be selected and configured based on application needs and is visualised through the FRACTAL System configurator. Hardware advances include a Hierarchical Adaptive Time‑Triggered Multicore Architecture (HATMA) that enables adaptation while balancing safety, security, power and environmental scenarios; it leverages an Adaptive Time‑Triggered Network on Chip (ATTNoC) for scheduling adaptation. An AI‑based metascheduler supports dependable, time‑critical scheduling and run‑time adaptation. The software stack uses microservices and provides data ingestion, storage, orchestration and containerised ML model servers; this ensures the same open architecture across low‑, mid‑ and high‑end edge nodes. FRACTAL validated its methodology through eight real‑world use cases, demonstrating the modular architecture and edge AI capabilities across domains
