Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Interpretable Nonroutine Network Traffic Prediction with a Case Study

Liangzhi Wang, Haoyuan Zhu, Jiliang Zhang, Zitian Zhang, Jie Zhang

TL;DR

A nonroutine network traffic prediction method to prospectively provide a theoretical basis for avoiding large-scale network disruption by accurately predicting bursty traffic and the numerical results indicate that the prediction closely fits the traffic pattern.

Abstract

This paper pioneers a nonroutine network traffic prediction (NNTP) method to prospectively provide a theoretical basis for avoiding large-scale network disruption by accurately predicting bursty traffic. Certain events that impact user behavior subsequently trigger nonroutine traffic, which significantly constrains the performance of network traffic prediction (NTP) models. By analyzing nonroutine traffic and the corresponding events, the NNTP method is pioneered to construct interpretable NTP model. Based on the real-world traffic data, the network traffic generated during soccer games serves as a case study to validate the performance of the NNTP method. The numerical results indicate that our prediction closely fits the traffic pattern. In comparison to existing researches, the NNTP method is at the forefront of finding a balance among interpretability, accuracy, and computational complexity.

Interpretable Nonroutine Network Traffic Prediction with a Case Study

TL;DR

A nonroutine network traffic prediction method to prospectively provide a theoretical basis for avoiding large-scale network disruption by accurately predicting bursty traffic and the numerical results indicate that the prediction closely fits the traffic pattern.

Abstract

This paper pioneers a nonroutine network traffic prediction (NNTP) method to prospectively provide a theoretical basis for avoiding large-scale network disruption by accurately predicting bursty traffic. Certain events that impact user behavior subsequently trigger nonroutine traffic, which significantly constrains the performance of network traffic prediction (NTP) models. By analyzing nonroutine traffic and the corresponding events, the NNTP method is pioneered to construct interpretable NTP model. Based on the real-world traffic data, the network traffic generated during soccer games serves as a case study to validate the performance of the NNTP method. The numerical results indicate that our prediction closely fits the traffic pattern. In comparison to existing researches, the NNTP method is at the forefront of finding a balance among interpretability, accuracy, and computational complexity.
Paper Structure (14 sections, 16 equations, 13 figures, 2 tables, 1 algorithm)

This paper contains 14 sections, 16 equations, 13 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. The Proposed NNTP Method with a Case Study
  4. Analysis of Nonroutine Traffic
  5. The Proposed NNTP Method
  6. Dataset for Nonroutine Traffic
  7. The Case Study: SG-NNTP Model
  8. Multistep Prediction of SG-NNTP
  9. Single-step Prediction of SG-NNTP
  10. Evaluation with Real-world Traffic Data
  11. Performance Comparison Between the SG-NNTP Model and the Benchmark Models in Multi-step Prediction Mode
  12. Performance of the SG-NNTP Model and Benchmark Models in Single-step Prediction Mode
  13. Analysis and Discussion
  14. Conclusion

Figures (13)

  • Figure 1: The daily traffic and the additive nonroutine traffic.
  • Figure 2: Cellular network traffic data in Milan published by Telecom Italia G. Barlacchi.
  • Figure 3: The information of the soccer games hosted by the San Siro Stadium in December 2013 Federico Botta.
  • Figure 4: SMS data for the soccer games held at the San Siro stadium in December.
  • Figure 5: The imitative effect of SG-NNTP model for the practical traffic.
  • ...and 8 more figures