Smart Car Parking: Temporal Clustering and Anomaly Detection in Urban Car Parking

A major challenge for modern cities is how to maximise the productivity and reliability of urban infrastructure, such as minimising road congestion by making better use of the limited car parking facilities that are available. To achieve this goal, there is growing interest in the capabilities of the emerging Internet of Things (IoT), which enables a wide range of physical objects and environments to be monitored in fine detail by using low-cost, low-power sensing and communication technologies. While there has been growing interest in the IoT for smart cities, there have been few systematic studies that can demonstrate whether practical insights can be extracted from real-life IoT data using advanced data analytics techniques. In this work, we consider a smart car parking scenario based on real-time car parking information that has been collected and disseminated by the City of San Francisco. We investigate whether useful trends and patterns can be automatically extracted from this rich and complex data set. We demonstrate that by using automated clustering and anomaly detection techniques we can identify potentially interesting trends and events in the data. To the best of our knowledge, we provide the first such analysis of the scope for clustering and anomaly detection on real-time car parking data in a major urban city.