KIGLIS: Smart Networks for Smart Cities
Daniel Bogdoll, Patrick Matalla, Christoph Füllner, Christian Raack, Shi Li, Tobias Käfer, Stefan Orf, Marc René Zofka, Finn Sartoris, Christoph Schweikert, Thomas Pfeiffer, André Richter, Sebastian Randel, Rene Bonk
TL;DR
Smart cities require networks that accommodate highly diverse services with strict QoS needs. The paper outlines Kiglis, an AI-enabled, fixed-mobile converged network approach that combines LoRa-WAN, PON, and 5G with a deep edge-cloud architecture to support automated driving, aiming for end-to-end latency around 1 ms. It proposes a service-driven methodology, classifies 30 city services into clusters, and emphasizes Remote Assistance as a central automated driving scenario, while detailing AI techniques for DSP optimization, data compression, network management, and infrastructure planning. Early results validate the service-driven analysis and smart-architecture framework and set the stage for a final demonstration in Karlsruhe, highlighting AI as a tool to reduce deployment costs and improve planning. The work has practical impact by guiding the design of scalable, low-latency smart city networks capable of integrating large-scale sensor data, human-in-the-loop assistance, and edge computing for automated driving and related services.
Abstract
Smart cities will be characterized by a variety of intelligent and networked services, each with specific requirements for the underlying network infrastructure. While smart city architectures and services have been studied extensively, little attention has been paid to the network technology. The KIGLIS research project, consisting of a consortium of companies, universities and research institutions, focuses on artificial intelligence for optimizing fiber-optic networks of a smart city, with a special focus on future mobility applications, such as automated driving. In this paper, we present early results on our process of collecting smart city requirements for communication networks, which will lead towards reference infrastructure and architecture solutions. Finally, we suggest directions in which artificial intelligence will improve smart city networks.