Electronic Devices Rutger Kerkhoff, Aleš Tavcar, Boštjan Kaluza 8 2 2019 https://doi.org/10.6025/ed/2019/8/2/43-49 http://www.dline.info/ed/fulltext/v8n2/edv8n2_3.pdf Creating simulations for smart cities is a complex and time consuming task. In this paper we show that using traditional Bayesian networks and real world data traces it is possible to infer models that can simulate the original domain. The created model can provide great insight into the actual subsystems that are considered. We show that given a set of observed values we can successfully use the created model to simulate data and show trends present in the original system.