MultiGran-STGCNFog: Towards Accurate and High-Throughput Inference for Multi-Granular Spatiotemporal Traffic Forecasting

2025-05-02

AI Summary

To address the challenge of jointly modeling multi-granularity spatiotemporal features and achieving low-latency inference in graph convolutional network (GCN)-based traffic forecasting, this paper proposes a distributed fog-end traffic prediction framework. Methodologically, we design a multi-granularity spatiotemporal graph convolutional model that integrates dynamic graph construction with multi-scale graph convolutions; further, we introduce GA-DPHDS—a novel genetic algorithm-driven hierarchical scheduling mechanism—that enables inter-layer pipelined execution and cooperative inference across heterogeneous fog–edge devices. Our key contributions include the first support for efficient multi-scale feature fusion and real-time scheduling on dynamic traffic graphs within fog computing environments. Evaluations on real-world datasets demonstrate up to 12.7% improvement in prediction accuracy, a 3.2× increase in inference throughput, and end-to-end latency at the millisecond level.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate traffic forecasting and swift inference provision are essential for intelligent transportation systems. However, the present Graph Convolutional Network (GCN)-based approaches cannot extract and fuse multi-granular spatiotemporal features across various spatial and temporal scales sufficiently, proven to yield less accurate forecasts. Besides, additional feature extraction branches introduced in prior studies critically increased model complexity and extended inference time, making it challenging to provide fast inference for traffic forecasting. In this paper, we propose MultiGran-STGCNFog, an efficient fog distributed inference system with a novel traffic forecasting model that employs multi-granular spatiotemporal feature fusion on generated dynamic traffic graphs to fully capture interdependent traffic dynamics. The proposed scheduling algorithm GA-DPHDS, optimizing layer execution order and layer-device scheduling scheme simultaneously, contributes to considerable inference throughput improvement by leveraging heterogeneous fog devices in a pipelined manner. Extensive experiments on real-world datasets demonstrate the superiority of the proposed method over selected baselines.

Problem

• Extracting multi-granular spatiotemporal features for accurate traffic forecasting
• Reducing model complexity to enable fast inference
• Optimizing layer execution and device scheduling for high throughput

Innovation

• Multi-granular spatiotemporal feature fusion
• Dynamic traffic graph generation
• Pipelined heterogeneous fog device scheduling