Enhanced FIWARE-Based Architecture for Cyberphysical Systems With Tiny Machine Learning and Machine Learning Operations: A Case Study on Urban Mobility Systems

TL;DR

This paper presents an enhanced FIWARE-based architecture integrating tinyML and MLOps for cyberphysical systems, demonstrated through a smart traffic system case study, emphasizing real-time, decentralized urban mobility solutions.

Contribution

It introduces an architecture managing the entire tinyML lifecycle within FIWARE, extending previous work to support edge computing and MLOps in cyberphysical systems.

Findings

Effective management of tinyML lifecycle in cyberphysical systems

Successful implementation of a smart traffic system using FIWARE

FIWARE ecosystem supports edge computing and tinyML deployment

Abstract

The rise of AI and the Internet of Things is accelerating the digital transformation of society. Mobility computing presents specific barriers due to its real-time requirements, decentralization, and connectivity through wireless networks. New research on edge computing and tiny machine learning (tinyML) explores the execution of AI models on low-performance devices to address these issues. However, there are not many studies proposing agnostic architectures that manage the entire lifecycle of intelligent cyberphysical systems. This article extends a previous architecture based on FIWARE software components to implement the machine learning operations flow, enabling the management of the entire tinyML lifecycle in cyberphysical systems. We also provide a use case to showcase how to implement the FIWARE architecture through a complete example of a smart traffic system. We conclude that the FIWARE ecosystem constitutes a real reference option for developing tinyML and edge computing in cyberphysical systems.