An Anthropocentric and Enhanced Predictive Approach to Smart City Management

Abstract

Cities are becoming increasingly complex to manage, as they increase in size and must provide higher living standards for their populations. New technology-based solutions must be developed towards attending this growth and ensuring that it is socially sustainable. This paper puts forward the notion that these solutions must share some properties: they should be anthropocentric, holistic, horizontal, multi-dimensional, multi-modal, and predictive. We propose an architecture in which streaming data sources that characterize the city context are used to feed a real-time graph of the city’s assets and states, as well as to train predictive models that hint into near future states of the city. This allows human decision-makers and automated services to take decisions, both for the present and for the future. To achieve this, multiple data sources about a city were gradually connected to a message broker, that enables increasingly rich decision-support. Results show that it is possible to predict future states of a city, in aspects such as traffic, air pollution, and other ambient variables. The key innovative aspect of this work is that, as opposed to the majority of existing approaches which focus on a real-time view of the city, we also provide insights into the near-future state of the city, thus allowing city services to plan ahead and adapt accordingly. The main goal is to optimize decision-making by anticipating future states of the city and make decisions accordingly.

Keywords

• Internet of Things
• smart cities
• machine learning