Past, Present, Future: A Comprehensive Exploration of AI Use Cases in the UMBRELLA IoT Testbed
This provides a guide for researchers and practitioners on implementing AI in real-world IoT systems, but it is incremental as it reviews existing applications and proposes future directions without introducing new methods.
The paper explores AI applications in the UMBRELLA IoT testbed, detailing four existing use cases such as automated streetlight monitoring and federated learning, and outlines future potential for smart cities and multi-robot systems.
UMBRELLA is a large-scale, open-access Internet of Things (IoT) ecosystem incorporating over 200 multi-sensor multi-wireless nodes, 20 collaborative robots, and edge-intelligence-enabled devices. This paper provides a guide to the implemented and prospective artificial intelligence (AI) capabilities of UMBRELLA in real-world IoT systems. Four existing UMBRELLA applications are presented in detail: 1) An automated streetlight monitoring for detecting issues and triggering maintenance alerts; 2) A Digital twin of building environments providing enhanced air quality sensing with reduced cost; 3) A large-scale Federated Learning framework for reducing communication overhead; and 4) An intrusion detection for containerised applications identifying malicious activities. Additionally, the potential of UMBRELLA is outlined for future smart city and multi-robot crowdsensing applications enhanced by semantic communications and multi-agent planning. Finally, to realise the above use-cases we discuss the need for a tailored MLOps platform to automate UMBRELLA model pipelines and establish trust.