Deep learning models for automated identification of scheduling policies
Author(s)
Chen, Yichong
Casale, Giuliano
Type
Conference Paper
Abstract
Queueing network models are commonly used asperformance models of distributed software applications and service-based systems. Although several methods exist for learning their parameters, such as demand estimation methods, little research has been carried out in the literature on automatically identifying scheduling policies from empirical datasets. Scheduling policies and their parameters have an impact on the model’sstationary distribution in general, thus their correct determi-nation is important for model accuracy. They are particularly relevant for correctly estimating percentiles and higher-order moments of performance indexes such as response times. Wepropose a deep learning technique based on transformer models- a common technique in natural language processing, to addressthe lack of methods for this parameter identification problem. From a sample path of the joint network state, or an aggregate thereof, our approach can classify the scheduling policy of thestations in a queueing network. We show that the transformer model delivers good-classification precision and recall, improving significantly over support vector machines or simpler recurrentneural networks.
Date Issued
2021-11-22
Date Acceptance
2021-09-05
Citation
2021, pp.1-8
Publisher
IEEE
Start Page
1
End Page
8
Copyright Statement
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Identifier
https://ieeexplore.ieee.org/document/9614298
Source
2021 29th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)
Publication Status
Published
Start Date
2021-11-03
Finish Date
2021-11-05
Coverage Spatial
Houston, TX, USA
Date Publish Online
2021-11-22