A Data Recovery Algorithm for Large-Scale Network Measurements: Association Learning Based Tensor Completion

被引：0
|
作者：
Ouyang Y.-D. [1 ]
Xie K. [1 ]
Xie G.-G. [2 ,3 ]
Wen J.-G. [1 ,4 ]
机构：
[1] College of Computer Science and Electronic Engineering, Hunan University, Hunan, Changsha
[2] Computer Network Information Center, Chinese Academy of Sciences, Beijing
[3] The University of Chinese Academy of Sciences, Beijing
[4] Hunan cnSunet Information Technology Co.，Ltd, Hunan, Changsha
来源：
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2022年 / 50卷 / 07期
关键词：
deep learning; multi-metrics association; network monitoring; sparse network measurement; tensor completion;
D O I：
10.12263/DZXB.20211703
中图分类号：
学科分类号：
摘要：
Network applications, such as network state tracking, service level agreement guarantee, and network fault location, rely on complete and accurate throughput measurement data. Due to the high measurement cost, it is hard to obtain network-wide throughput measurement data for network monitoring systems. Sparse network measurement techniques reduce the measurement cost based on sampling and recover missing data from partial network measurement data by exploiting spatio-temporal correlations within the data through algorithms such as tensor completion. However, existing studies only consider individual performance metrics and ignore the correlation information between multiple metrics, resulting in limited recovery accuracy and high overall measurement cost. This paper proposes a data recovery algorithm for large-scale network measurements-association learning based tensor completion(ALTC). To capture the complex correlations among network performance metrics, an association learning model is designed to reduce the network measurement cost by using the round-trip delay with low measurement overhead to infer the throughput with high measurement overhead. Based on this, a tensor completion model is designed to learn both the spatio-temporal correlation within the throughput measurement data and the external auxiliary correlation information from the round-trip delay, and finally obtain the network-wide throughput data with higher recovery accuracy. Experiments show that the recovery error of the proposed algorithm is 13% lower than that of the current mainstream methods at the same throughput measurement cost, achieving better recovery results. © 2022 Chinese Institute of Electronics. All rights reserved.
引用
收藏
页码：1653 / 1663
页数：10
相关论文
共 30 条
  • [1] CUNHA I, TEIXEIRA R, VEITCH D, Et al., Predicting and tracking internet path changes, Proceedings of the ACM SIGCOMM 2011 Conference, pp. 122-133, (2011)
  • [2] JAIN S, KUMAR A, MANDAL S, Et al., B4: Experience with a globally-deployed software defined wan, SIGCOMM'13: Proceedings of the ACM SIGCOMM 2013 conference on SIGCOMM, pp. 3-14, (2013)
  • [3] PENG Y H, YANG J, WU C, Et al., deTector: A topology-aware monitoring system for data center networks, Proceedings of the 2017 USENIX Annual Technical Conference, pp. 55-68, (2017)
  • [4] MATHIS M, ALLMAN M., A Framework for Defining Empirical Bulk Transfer Capacity Metrics, (2001)
  • [5] ZENG B., Researches on Internet Performance Monitoring Based on Active Measurements, (2009)
  • [6] BREITBART Y, CHAN -Y, GAROFALAKIS M, Et al., Efficiently monitoring bandwidth and latency in IP networks, Proceedings IEEE INFOCOM 2001, Conference on Computer Communications, Twentieth Annual Joint Conference of the IEEE Computer and Communications Society(Cat. No. 01CH37213), pp. 933-942, (2001)
  • [7] CLAISE B, SADASIVAN G, VALLURI V, Et al., Cisco systems netflow services export version 9, RFC 3954
  • [8] TOOTOONCHIAN A, GHOBADI M, GANJALI Y., OpenTM: Traffic matrix estimator for OpenFlow networks, International Conference on Passive and Active Network Measurement, pp. 201-210, (2010)
  • [9] GUO C X, YUAN L H, XIANG D, Et al., Pingmesh: A large-scale system for data center network latency measurement and analysis, SIGCOMM'15: Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication, pp. 139-152, (2015)
  • [10] XIE K, WANG L L, WANG X, Et al., Sequential and adaptive sampling for matrix completion in network monitoring systems, 2015 IEEE Conference on Computer Communications, pp. 2443-2451, (2015)
123