Meta-Guided Graph Lightweight TimesNet for Traffic Prediction in Internet of Vehicles

Accurate and efficient traffic flow prediction is crucial for the increasingly prevalent autonomous driving, enabling more advanced intelligent transportation systems. For this purpose, we propose a novel model termed Meta Guided-Graph Lightweight TimesNet (MGGLTN) to accurately capture the spatio-temporal correlations within traffic flow data, thereby providing precise traffic flow predictions for Connected Vehicles (CVs). Our spatio-temporal information learning architecture features an encoder-decoder backbone, wherein both the encoder and decoder comprise graph convolutional networks coupled with lightweight Times modules. More importantly, we propose a meta guided-graph library, aimed at providing memory queries for time-varying traffic patterns based on real-world physical spatial information. It efficiently guides the initialization direction of meta guided-graph prototypes, thereby accelerating the convergence speed of model training. Moreover, we introduce depthwise separable convolutions to replace the computationally intensive multi-kernel convolutions in the Times modules, thus significantly reducing computational costs and model parameters while maintaining accuracy. We perform extensive experiments on three public benchmark datasets (i.e., METR-LA, PEMS-BAY, and EXPY-TKY) and conduct comprehensive performance evaluations compared to both baseline models and state-of-the-art models. The findings demonstrate the superior performance of our model across all three datasets of varying spatial scales, highlighting the potential of this model to provide precise traffic guidance for CVs.