Paper Info
Title
Data-driven Learning to Predict WAN Network Traffic
Abstract
In this paper, we explore both statistical and deep learning approaches for multi-step predictions in WAN traffic traces. Estimating future traffic can help improve link usage and optimize bandwidth utilization. In this paper, we study real network traces from a real WAN research network. We use Fourier analysis to present variation among the traffic traces, extracting daily and weekly peak frequencies per trace. We also develop statistical time-series methods, ARIMA and Holt-Winters, and three LSTM-based approaches with various neural network architectures (Simple, Stacked and S2S LSTM), to forecast and compare the accuracies between them. With efforts to find a data-driven learning solution, we find that deep learning approaches can learn traffic patterns and provide more accurate predictions than ARIMA and Holt-Winters. Our results show that predictions are improved at an average of 70% or more. We further discuss the challenges of building these, their deployment and how these can help improve network utilization for future planning problems.
Year
DOI
Venue
2020
10.1145/3391812.3396268
HPDC '20: The 29th International Symposium on High-Performance Parallel and Distributed Computing Stockholm Sweden June, 2020
DocType
ISBN
Citations 
Conference
978-1-4503-7980-9
2
PageRank 
References 
Authors
0.40
0
4
Name
Order
Citations
PageRank
Nandini Krishnaswamy120.40
Mariam Kiran212117.83
Kunal Singh320.40
Bashir Mohammed421.75