Mensageria: A smart city framework for real-time analysis of traffic data streams

Abstract

Several smart city systems have focused on addressing a specific mobility problem scenario (e.g., air pollution, traffic jam) in a given city. The task of adding, extending, or porting the smart city scenario to other cities can be very challenging due to the rigid structure of such existing systems. To address this issue, in this paper we investigate common programming constructors that can be used to leverage the construction of such dynamic, smart city systems in the mobility domain. We propose Mensageria, a framework based on both the Complex Event Processing data-streaming processing paradigm and relational database management systems, which can dynamically deploy new or extend existing smart city scenarios in near real-time and maintain an updated dataset for provenance purposes. Mensageria provides several real-time primitives, such as filter, join, and enrich, that can be used to integrate, process, and analyze the city entities data streams. We discuss the generality, performance, and limitations of the proposed constructs through a real-world case study that was used in the Olympic Games of Rio in 2016 to detect, in real-time, existing and new situations that could affect the city mobility infrastructure.