Multi-Agent Systems and Digital Twins for Smarter Cities

Abstract

An intelligent combination of the Internet of Things (IoT) and approaches to modeling and simulation is one of the most challenging endeavors for future cities, manufacturing industries, and predictive maintenance. Digital Twins take on a unique role here. However, the question of what a Digital Twin is and what differentiates it from a regular model is still open. We present an experimental setup for integrating an existing simulation model of Hamburg's traffic system with the city's real-time sensor network. The Digital Twin is implemented using the large-scale multi-agent framework MARS. The entire process from the model description to retrieving real-time data from the IoT sensors and incorporating it in the simulation is presented. As a first prototypical example, a multi-modal mobility model was connected to real-world bike-sharing locations in Hamburg. We find that the combination of multi-agent systems and IoT sensors as a Digital Twin shows enormous potential for city planners, policy stakeholders, and other decision-makers. By correcting the course of a simulation via real-time data, the corridor-of-uncertainty that is intrinsic to some simulation models' use can be reduced significantly. Furthermore, any divergence of simulated and sampled data can lead to a deeper understanding of complex adaptive systems like big cities.