Compreendendo o Desempenho de Gerenciadores de Contexto para Internet das Coisas

Context-Aware Management Systems have been proposed in the last years to perform automatic decision making for the Internet of Things. Although scalability is an indispensable feature for those systems, there are no comprehensive results reporting their performance. This paper shows results of a performance analysis study of different context-aware architectures and introduces the SenSE platform for generating sensor synthetic data. Results show that different architectural choices impact system scalability and that automatic real time decision-making is feasible in an environment composed of dozens of thousands of sensors that continuously transmit data.