Log In Sign Up

Dynamic Graph Neural Network for Traffic Forecasting in Wide Area Networks

by   Tanwi Mallick, et al.

Wide area networking infrastructures (WANs), particularly science and research WANs, are the backbone for moving large volumes of scientific data between experimental facilities and data centers. With demands growing at exponential rates, these networks are struggling to cope with large data volumes, real-time responses, and overall network performance. Network operators are increasingly looking for innovative ways to manage the limited underlying network resources. Forecasting network traffic is a critical capability for proactive resource management, congestion mitigation, and dedicated transfer provisioning. To this end, we propose a nonautoregressive graph-based neural network for multistep network traffic forecasting. Specifically, we develop a dynamic variant of diffusion convolutional recurrent neural networks to forecast traffic in research WANs. We evaluate the efficacy of our approach on real traffic from ESnet, the U.S. Department of Energy's dedicated science network. Our results show that compared to classical forecasting methods, our approach explicitly learns the dynamic nature of spatiotemporal traffic patterns, showing significant improvements in forecasting accuracy. Our technique can surpass existing statistical and deep learning approaches by achieving approximately 20 error for multiple hours of forecasts despite dynamic network traffic settings.


page 1

page 3

page 5

page 6


Transfer Learning with Graph Neural Networks for Short-Term Highway Traffic Forecasting

Highway traffic modeling and forecasting approaches are critical for int...

Graph-Partitioning-Based Diffusion Convolution Recurrent Neural Network for Large-Scale Traffic Forecasting

Traffic forecasting approaches are critical to developing adaptive strat...

Forecasting Busy-Hour Downlink Traffic in Cellular Networks

The dramatic growth in cellular traffic volume requires cellular network...

Graph Neural Networks for Traffic Forecasting

The significant increase in world population and urbanisation has brough...

Deep-Ensemble-Based Uncertainty Quantification in Spatiotemporal Graph Neural Networks for Traffic Forecasting

Deep-learning-based data-driven forecasting methods have produced impres...

RiskOracle: A Minute-level Citywide Traffic Accident Forecasting Framework

Real-time traffic accident forecasting is increasingly important for pub...

Computing System Congestion Management Using Exponential Smoothing Forecasting

An overloaded computer must finish what it starts and not start what wil...