Semantic Interoperability in Smart Cities: A Distributed Architecture Based on Ontologies, Plug-and-Play AI, and BlockDAG

Abstract

Smart City platforms increasingly depend on sensing devices and distributed services. The implementation of data-driven mobility systems and infrastructure management has not solved the problem of semantic interoperability. The problem comes from data models in middleware solutions and from the lack of support for devices connecting on their own. Existing approaches often struggle to scale under high data rates and dynamic environments. We presents a work-in-progress distributed architecture that combines semantic technologies, Plug-and-Play Artificial Intelligence (PnP-AI), and a Directed Acyclic Graph (DAG)-based synchronization layer that aims to enable decentralized semantic interoperability in Smart City scenarios. The system applies an Intelligent Transportation System ontology to perform semantic labeling of sensor observation, Shapes Constraint Language (SHACL) shapes for local semantic validation, and a lightweight PnP-AI agent with a Decision Tree classifier to perform automatic device categorization during onboarding. The system design allows nodes to perform processing operations and validation tasks while semantically validated events are propagated through a DAG-based ledger without relying on centralized middleware. Preliminary experimental results from a simulated multi-node environment showed that end-to-end latency remained under 15 ms and throughput reached more than 100 events per second while all messages successfully passed SHACL validation. These results show that the architecture can improve scalability and resilience compared to centralized middleware systems. Current efforts are directed toward expanding the test scope, incorporating security and privacy mechanisms, and demonstrating the approach in more complex urban mobility scenarios.