Accurate Recovery of Internet Traffic Data Under Variable Rate Measurements

Authors:
Publisher website
Google Scholar
Abstract
The inference of the network traffic matrix from partial measurement data becomes increasingly critical for various network engineering tasks, such as capacity planning, load balancing, path setup, network provisioning, anomaly detection, and failure recovery. The recent study shows it is promising to more accurately interpolate the missing data with a 3-D tensor as compared with the interpolation methods based on a 2-D matrix. Despite the potential, it is difficult to form a tensor with measurements taken at varying rate in a practical network. To address the issues, we propose a Reshape-Align scheme to form the regular tensor with data from variable rate measurements, and introduce user-domain and temporal-domain factor matrices which take full advantage of features from both domains to translate the matrix completion problem to the tensor completion problem based on CANDECOMP/PARAFAC decomposition for more accurate missing data recovery. Our performance results demonstrate that our Reshape-Align scheme can achieve significantly better performance in terms of several metrics: error ratio, mean absolute error, and root mean square error.
Funding Information
  • National Natural Science Foundation of China (61572184, 61725206, 61472130, 61472131, 61772191)
  • Hunan Provincial Natural Science Foundation of China (2017JJ1010)
  • Science and Technology Key Projects of Hunan Province (2015TP1004, 2016JC2012)
  • U.S. ONR (N00014-17-1-2730)
  • NSF (ECCS 1408247, CNS 1526843, ECCS 1731238)
  • open project funding of the CAS Key Laboratory of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences (CASNDST201704)

This publication has 39 references indexed in Scilit: