Modelo e algoritmos para seleção de sensores como serviço

Abstract

The Internet of Things (IoT) plays a key role in the future of the Internet, as it will inte-grate billions of smart devices which will present sensing, actuation and data processingcapabilities. Thus, each integrated device may have one or more built-in sensors thatwill potentially generate huge amounts of data. This scenario raises the challenge ofefficiently searching and selecting the most appropriate sensors within a set that canpresent similar functionalities and capabilities. In this context, this work presents a math-ematical model for sensor selection able to maximize the attendance to user input re-quirements, such as accuracy, robustness, and availability for different types of sensors(such as temperature, pressure, humidity, wind speed, and so on) in a limited budget.This model was tested through two algorithms, the first being an optimization algorithmand the second a greedy heuristic. These solutions were evaluated and compared interms of three criteria: the optimization time, the amount of budget being utilized, andthe optimal value. The best solutions were found by the optimization algorithm but, thegreedy heuristic found close results. In some cases, the greedy heuristic found solu-tions more than 10x faster when compared to the Optimal Algorithm.