Du-Parking: Spatio-Temporal Big Data Tells You Realtime Parking Availability
Yuecheng Rong (Baidu); Zhimian Xu (Baidu); Ruibo Yan (Baidu); Xu Ma (Baidu)
Realtime parking availability information is of great importance to help drivers to find a parking space faster and thus to reduce parking search traffic. While there are limited realtime parking availability systems in a city due to the expensive cost of sensor device and maintaining realtime parking information. In this paper, we estimate the realtime parking availability throughout a city using historical parking availability data reported by a limited number of existing sensors of parking lots and a variety of datasets we observed in the city, such as meteorology, events, map mobility trace data and navigation data from Baidu map, and POIs. We propose a deep-learning-based approach, called Du-Parking, which consists of three major components modeling temporal closeness, period and current general influence, respectively. More specifically, we employ long short-term memory (LSTM) to model the temporal closeness and period, and meanwhile using two fully-connected layers to model the current general factors. Our approach learns to dynamically aggregate the output of the three components, to estimate the final parking availability of given parking lot. Using the proposed approach, we have provided the realtime parking availability information in Baidu map app, in nine cities in China. We evaluated our approach in Beijing and Shenzhen. The results show the advantages of our method over two categories of baselines, including linear interpolations, and the well-known classification model like GBDT.