Advanced IoT Edge Architecture for Smart City

In the last few years, terms like Internet of Things, Cloud Computing and Edge Computing have captured a lot of attention from both scientific and industrial perspectives. They are independent but closely related concepts, and their use extends into several scenarios, such as Smart Agriculture, Smart Home, autonomous vehicles, and Smart City, to name but a few. Among the Smart City solutions, Smart Parking aims to solve the problem of parking space and parking management in big cities, since the search for free parking spaces brings along a serious cost, air pollution and stress issues. The objective of this article is to propose an Edge Computing architecture tailored for Smart Parking solutions, addressing the challenges of real-time data processing and efficient parking management. This architecture integrates a Deep Learning solution based on Gated Recurrent Units (GRU) to accurately forecast the number of available and occupied parking spaces.