Adaptive Multi-receptive Field Spatial-Temporal Graph Convolutional Network for Traffic Forecasting

TL;DR

This paper introduces AMF-STGCN, a novel deep learning model that effectively captures complex spatial-temporal dependencies in mobile network traffic, improving multi-step forecasting accuracy over existing methods.

Contribution

The paper presents a new adaptive multi-receptive field spatial-temporal graph convolutional network for mobile traffic forecasting, integrating attention mechanisms and an extra decoder for better multi-step predictions.

Findings

AMF-STGCN outperforms state-of-the-art methods on four real-world datasets.

The model effectively captures heterogeneous spatial-temporal dependencies.

The approach reduces error propagation in multi-step forecasting.

Abstract

Mobile network traffic forecasting is one of the key functions in daily network operation. A commercial mobile network is large, heterogeneous, complex and dynamic. These intrinsic features make mobile network traffic forecasting far from being solved even with recent advanced algorithms such as graph convolutional network-based prediction approaches and various attention mechanisms, which have been proved successful in vehicle traffic forecasting. In this paper, we cast the problem as a spatial-temporal sequence prediction task. We propose a novel deep learning network architecture, Adaptive Multi-receptive Field Spatial-Temporal Graph Convolutional Networks (AMF-STGCN), to model the traffic dynamics of mobile base stations. AMF-STGCN extends GCN by (1) jointly modeling the complex spatial-temporal dependencies in mobile networks, (2) applying attention mechanisms to capture various Receptive Fields of heterogeneous base stations, and (3) introducing an extra decoder based on a fully connected deep network to conquer the error propagation challenge with multi-step forecasting. Experiments on four real-world datasets from two different domains consistently show AMF-STGCN outperforms the state-of-the-art methods.