Learning Queuing Networks by Recurrent Neural Networks

被引:8
|
作者
Garbi, Giulio [1 ]
Incerto, Emilio [1 ]
Tribastone, Mirco [1 ]
机构
[1] IMT Sch Adv Studies Lucca, Lucca, Italy
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
下载
收藏
页码:56 / 66
页数:11
相关论文
共 50 条
  • [1] LEARNING IN RECURRENT NEURAL NETWORKS
    WHITE, H
    MATHEMATICAL SOCIAL SCIENCES, 1991, 22 (01) : 102 - 103
  • [2] Learning with recurrent neural networks - Conclusion
    不详
    LEARNING WITH RECURRENT NEURAL NETWORKS, 2000, 254 : 133 - 135
  • [3] LEARNING COMPACT RECURRENT NEURAL NETWORKS
    Lu, Zhiyun
    Sindhwani, Vikas
    Sainath, Tara N.
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 5960 - 5964
  • [4] Bayesian learning for recurrent neural networks
    Crucianu, M
    Boné, R
    de Beauville, JPA
    NEUROCOMPUTING, 2001, 36 (01) : 235 - 242
  • [5] Learning with recurrent neural networks - Introduction
    Hammer, B
    LEARNING WITH RECURRENT NEURAL NETWORKS, 2000, 254 : 1 - +
  • [6] Hebbian learning of context in recurrent neural networks
    Brunel, N
    NEURAL COMPUTATION, 1996, 8 (08) : 1677 - 1710
  • [7] Stable reinforcement learning with recurrent neural networks
    James Nate KNIGHT
    Charles ANDERSON
    Control Theory and Technology, 2011, 9 (03) : 410 - 420
  • [8] Learning to Adaptively Scale Recurrent Neural Networks
    Hu, Hao
    Wang, Liqiang
    Qi, Guo-Jun
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 3822 - 3829
  • [9] Convergence result for learning in recurrent neural networks
    Kuan, Chung-Ming
    Hornik, Kurt
    White, Halbert
    Neural Computation, 1994, 6 (03)
  • [10] Convergence of diagonal recurrent neural networks' learning
    Wang, P
    Li, YF
    Feng, S
    Wei, W
    PROCEEDINGS OF THE 4TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-4, 2002, : 2365 - 2369