Utilizando dados históricos para realizar previsões em smart campus

Abstract

The growing process of globalization is making the sustainable development of cities a great challenge and to be aware that they must be careful for sustainable consumption and leave resources for the next generations. About 60% of the electricity generated in the world is consumed between the United States and China alone, and this situation is exacerbated by the fact that these non-renewable sources degrade the environment. The main objective of Smart Cities is, in fact, to make cities a better place to live in now and, in the long run, to put citizens at the center. To achieve this goal, Smart Cities rely on the Internet of Things (IoT) paradigm, so Information and Communication Technology (ICT) is intensively applied in all areas related to the well-being of citizens, such as transport and mobility, health, energy or the environment. This means that society needs to better manage its resources so as not to create scarcity. However, the Internet of Things (IoT) is an ally of Artificial Intelligence that brings the idea of intelligent environments that insert computing into the physical world in order to monitor and automate everyday activities, identify patterns and make predictions. In this work, an IoT solution is proposed for the storage of historical data from sensors installed on the Quixadá Campus for the monitoring of intelligent environments. In this way, the procedures for construction and configuration of the different parts of the project, such as the implementation of QuantumLeap in the Cloud, which is responsible for receiving the notification and storing the data in its database, using the Fiware platform. The library was also presented for the treatment and realization of time series forecasts and the integration with the Dashboard for data visualization. In addition, tests were carried out and the results were promising, indicating that the solution has a great contribution to the Campus and managers.