Learning Queuing Networks by Recurrent Neural Networks

被引:9
作者
Garbi, Giulio [1 ]
Incerto, Emilio [1 ]
Tribastone, Mirco [1 ]
机构
[1] IMT Sch Adv Studies Lucca, Lucca, Italy
来源
PROCEEDINGS OF THE ACM/SPEC INTERNATIONAL CONFERENCE ON PERFORMANCE ENGINEERING (ICPE'20) | 2020年
关键词
software performance; queuing networks; recurrent neural networks; PERFORMANCE PREDICTION; INFERENCE; SYSTEMS; DEMAND;
D O I
10.1145/3358960.3379134
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
It is well known that building analytical performance models in practice is difficult because it requires a considerable degree of proficiency in the underlying mathematics. In this paper, we propose a machine-learning approach to derive performance models from data. We focus on queuing networks, and crucially exploit a deterministic approximation of their average dynamics in terms of a compact system of ordinary differential equations. We encode these equations into a recurrent neural network whose weights can be directly related to model parameters. This allows for an interpretable structure of the neural network, which can be trained from system measurements to yield a white-box parameterized model that can be used for prediction purposes such as what-if analyses and capacity planning. Using synthetic models as well as a real case study of a load-balancing system, we show the effectiveness of our technique in yielding models with high predictive power.
引用
收藏
页码:56 / 66
页数:11
相关论文
共 64 条
  • [1] Abadi M., 2015, TENSORFLOW LARGE SCA
  • [2] Software Architecture Optimization Methods: A Systematic Literature Review
    Aleti, Aldeida
    Buhnova, Barbora
    Grunske, Lars
    Koziolek, Anne
    Meedeniya, Indika
    [J]. IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2013, 39 (05) : 658 - 683
  • [3] [Anonymous], 2013, ASE
  • [4] [Anonymous], 2011, P 7 INT C NETW SERV
  • [5] Control Theory for Model-based Performance-driven Software Adaptation
    Arcelli, Davide
    Cortellessa, Vittorio
    Filieri, Antonio
    Leva, Alberto
    [J]. QOSA'15 PROCEEDINGS OF THE 11TH INTERNATIONAL ACM SIGSOFT CONFERENCE ON QUALITY OF SOFTWARE ARCHITECTURES, 2015, : 11 - 20
  • [6] Ascher U.M., 1988, COMPUTER METHODS ORD
  • [7] Awad Mahmoud, 2017, ICPE
  • [8] Model-based performance prediction in software development: A survey
    Balsamo, S
    Di Marco, A
    Inverardi, P
    Simeoni, M
    [J]. IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2004, 30 (05) : 295 - 310
  • [9] Balsamo Simonetta, 2005, WOSP
  • [10] Bolch G., 2005, Queueing networks and Markov chains