MV-STGCN: Multi-view Spatial-Temporal Graph Convolutional Networks for On-Street Parking Availability Prediction

Abstract

Smart cities leverage advancements in big data and artificial intelligence to deliver a multitude of services and information to urban people. Among these services, predicting on-street parking availability is an important application with the potential to enhance parking efficiency, alleviate city congestion, and minimize pollution. Existing methods for forecasting parking occupancy rates mostly rely on recurrent neural networks (RNNs) to capture temporal dimension information from parking time series data. However, these methods typically overlook the crucial spatial dependency among parking areas, resulting in suboptimal prediction accuracy. Furthermore, the computationally intensive nature of RNN-based methods leads to slow prediction speeds. To address these limitations, we propose Multi-view Spatial-temporal Graph Convolutional Networks (MV-STGCN) to predict parking occupancy rates. By integrating spatial and temporal features, MV-STGCN is able to capture complex spatial-temporal correlations and improve prediction accuracy while optimizing prediction speed. The proposed MV-STGCN incorporates a multi-view contrastive Graph Convolution module (mvc-GConv), which employs a multi-view contrast method to extract features from topology and feature spaces with commonalities and differences in a multi-view way. Experimental results based on real-world datasets demonstrate that MV-STGCN outperforms baselines in predicting long-term parking occupancy rates while achieving superior prediction speed.