As we transition from the information age to the age of intelligence, data is no longer the sole asset; rather, it is the intelligence derived from it that holds value at the edge of the network. Current edge intelligence research primarily focuses on two directions: utilizing AI for edge resource management and deploying lightweight AI models on edge devices. However, existing edge computing research lacks an intelligence-centric framework where derived intelligence is treated as a first-class, independently manageable entity that can be described, discovered, observed, shared, reused, and dynamically clustered across heterogeneous edge devices and applications.
To address these research gaps, we introduce Clustered Edge Intelligence (CEI), a visionary intelligence-centric approach. The aim of CEI is to make intelligence a shareable and reusable first-class entity that can be independently represented, discovered, observed, exchanged, and managed across the distributed edge-cloud continuum.
We present a three-layer CEI architecture and examine enabling technologies and research dimensions, including intelligence inventories, semantic knowledge representation, communication, discoverability, observability, lifecycle automation, clustering mechanisms, marketplaces, interoperability, and standardization.
Blogger's Review: The introduction of Clustered Edge Intelligence offers a fresh perspective on the integration of edge computing and AI, emphasizing the sharing and reusability of intelligence, which will drive further advancements in edge computing, especially in heterogeneous environments. Its three-layer architecture design will also provide crucial guidance for the implementation of related technologies.