Artificial Intelligence Applications and Self-Learning 6G Networks for Smart Cities Digital Ecosystems: Taxonomy, Challenges, and Future Directions

Abstract

The recent upsurge of smart cities’ applications and their building blocks in terms of the Internet of Things (IoT), Artificial Intelligence (AI), federated and distributed learning, big data analytics, blockchain, and edge-cloud computing has urged the design of the upcoming 6G network generation, due to their stringent requirements in terms of the quality of services (QoS), availability, and dependability to satisfy a Service-Level-Agreement (SLA) for the end users. Industries and academia have started to design 6G networks and propose the use of AI in its protocols and operations. Published papers on the topic discuss either the requirements of applications via a top-down approach or the network requirements in terms of agility, performance, and energy saving using a down-top perspective. In contrast, this paper adopts a holistic outlook, considering the applications, the middleware, the underlying technologies, and the 6G network systems towards an intelligent and integrated computing, communication, coordination, and decision-making ecosystem. In particular, we discuss the temporal evolution of the wireless network generations’ development to capture the applications, middleware, and technological requirements that led to the development of the network generation systems from 1G to AI-enabled 6G and its employed self-learning models. We provide a taxonomy of the technology-enabled smart city applications’ systems and present insights into those systems for the realization of a trustworthy and efficient smart city ecosystem. We propose future research directions in 6G networks for smart city applications.