Published on Fri Aug 28 2020

Dynamic Graph Neural Network for Traffic Forecasting in Wide Area Networks

Tanwi Mallick, Mariam Kiran, Bashir Mohammed, Prasanna Balaprakash

Wide area networking infrastructures (WANs) are the backbone for moving large volumes of scientific data. WANs are struggling to cope with large data volumes, real-time responses, and overall network performance. Forecasting network traffic is a critical capability for proactive resource management.

0
0
0
Abstract

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% mean absolute percentage error for multiple hours of forecasts despite dynamic network traffic settings.

Mon Jan 25 2021
Machine Learning
Deep Graph Convolutional Networks for Wind Speed Prediction
Wind speed prediction and forecasting is important for various business and management sectors. In this paper, we introduce new models for wind speed Prediction based on graph convolutional networks (GCNs)
0
0
0
Wed Dec 11 2019
Machine Learning
Incrementally Improving Graph WaveNet Performance on Traffic Prediction
Graph WaveNet (GWN) interleaves graph convolution to aggregate information from nearby sensors and dilated convolutions to aggregate information from the past. The goal of this task is to predict the future speed of traffic at each sensor in a network using the past hour of sensor readings.
0
0
0
Wed May 12 2021
Machine Learning
An Empirical Experiment on Deep Learning Models for Predicting Traffic Data
0
0
0
Mon Jan 13 2020
Machine Learning
Fast-Fourier-Forecasting Resource Utilisation in Distributed Systems
Distributed computing systems often consist of hundreds of nodes, executing different resource requirements. Efficient resource provisioning and task scheduling in such systems are non-trivial and require close monitoring and accurate forecasting.
0
0
0
Tue Apr 27 2021
Artificial Intelligence
Graph Neural Networks for Traffic Forecasting
0
0
0
Wed Jan 27 2021
Artificial Intelligence
Graph Neural Network for Traffic Forecasting: A Survey
Traffic forecasting is important for the success of intelligent transportation systems. In recent years, graph neural networks have been introduced and have achieved state-of-the-art performance in a series of traffic forecasting problems. To the best of our knowledge, this paper is the first comprehensive survey that explores
0
0
0