Fourier trajectory analysis for identifying system congestion

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

We examine the use of the Fourier transform to discriminate dynamic behavior differences between congested and uncongested systems. Simulation continuous time statistic 'trajectories' are converted to time series for Fourier analysis. The pattern of Fourier component magnitudes across frequencies differs for congested versus uncongested systems. We use this knowledge to explore statistical process control methods to monitor nonstationary systems for transition from uncongested to congested state and vice versa. In a sense we are monitoring dynamic metamodel parameters to detect change in the dynamic behavior of the simulation. CUSUM charts on Fourier magnitudes can detect such transitions, and preliminary results suggest that in some cases detection can be more rapid than for CUSUM charts based on queue length.

Original languageEnglish (US)
Title of host publication2016 Winter Simulation Conference
Subtitle of host publicationSimulating Complex Service Systems, WSC 2016
EditorsTheresa M. Roeder, Peter I. Frazier, Robert Szechtman, Enlu Zhou
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages401-412
Number of pages12
ISBN (Electronic)9781509044863
DOIs
StatePublished - Jul 2 2016
Event2016 Winter Simulation Conference, WSC 2016 - Arlington, United States
Duration: Dec 11 2016Dec 14 2016

Publication series

NameProceedings - Winter Simulation Conference
Volume0
ISSN (Print)0891-7736

Other

Other2016 Winter Simulation Conference, WSC 2016
CountryUnited States
CityArlington
Period12/11/1612/14/16

Fingerprint

CUSUM Chart
Congestion
Trajectories
Trajectory
Dynamic Behavior
Statistical Process Control
Statistical process control
Fourier analysis
Fourier Analysis
Queue Length
Metamodel
Statistic
Continuous Time
Time series
Fourier transform
Fourier transforms
Monitor
Simulation
Statistics
Monitoring

All Science Journal Classification (ASJC) codes

  • Software
  • Modeling and Simulation
  • Computer Science Applications

Cite this

Wu, X., & Barton, R. R. (2016). Fourier trajectory analysis for identifying system congestion. In T. M. Roeder, P. I. Frazier, R. Szechtman, & E. Zhou (Eds.), 2016 Winter Simulation Conference: Simulating Complex Service Systems, WSC 2016 (pp. 401-412). [7822107] (Proceedings - Winter Simulation Conference; Vol. 0). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WSC.2016.7822107
Wu, Xinyi ; Barton, Russell R. / Fourier trajectory analysis for identifying system congestion. 2016 Winter Simulation Conference: Simulating Complex Service Systems, WSC 2016. editor / Theresa M. Roeder ; Peter I. Frazier ; Robert Szechtman ; Enlu Zhou. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 401-412 (Proceedings - Winter Simulation Conference).
@inproceedings{ceb30f27d6f74aa79e3d2770bddda5e7,
title = "Fourier trajectory analysis for identifying system congestion",
abstract = "We examine the use of the Fourier transform to discriminate dynamic behavior differences between congested and uncongested systems. Simulation continuous time statistic 'trajectories' are converted to time series for Fourier analysis. The pattern of Fourier component magnitudes across frequencies differs for congested versus uncongested systems. We use this knowledge to explore statistical process control methods to monitor nonstationary systems for transition from uncongested to congested state and vice versa. In a sense we are monitoring dynamic metamodel parameters to detect change in the dynamic behavior of the simulation. CUSUM charts on Fourier magnitudes can detect such transitions, and preliminary results suggest that in some cases detection can be more rapid than for CUSUM charts based on queue length.",
author = "Xinyi Wu and Barton, {Russell R.}",
year = "2016",
month = "7",
day = "2",
doi = "10.1109/WSC.2016.7822107",
language = "English (US)",
series = "Proceedings - Winter Simulation Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "401--412",
editor = "Roeder, {Theresa M.} and Frazier, {Peter I.} and Robert Szechtman and Enlu Zhou",
booktitle = "2016 Winter Simulation Conference",
address = "United States",

}

Wu, X & Barton, RR 2016, Fourier trajectory analysis for identifying system congestion. in TM Roeder, PI Frazier, R Szechtman & E Zhou (eds), 2016 Winter Simulation Conference: Simulating Complex Service Systems, WSC 2016., 7822107, Proceedings - Winter Simulation Conference, vol. 0, Institute of Electrical and Electronics Engineers Inc., pp. 401-412, 2016 Winter Simulation Conference, WSC 2016, Arlington, United States, 12/11/16. https://doi.org/10.1109/WSC.2016.7822107

Fourier trajectory analysis for identifying system congestion. / Wu, Xinyi; Barton, Russell R.

2016 Winter Simulation Conference: Simulating Complex Service Systems, WSC 2016. ed. / Theresa M. Roeder; Peter I. Frazier; Robert Szechtman; Enlu Zhou. Institute of Electrical and Electronics Engineers Inc., 2016. p. 401-412 7822107 (Proceedings - Winter Simulation Conference; Vol. 0).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Fourier trajectory analysis for identifying system congestion

AU - Wu, Xinyi

AU - Barton, Russell R.

PY - 2016/7/2

Y1 - 2016/7/2

N2 - We examine the use of the Fourier transform to discriminate dynamic behavior differences between congested and uncongested systems. Simulation continuous time statistic 'trajectories' are converted to time series for Fourier analysis. The pattern of Fourier component magnitudes across frequencies differs for congested versus uncongested systems. We use this knowledge to explore statistical process control methods to monitor nonstationary systems for transition from uncongested to congested state and vice versa. In a sense we are monitoring dynamic metamodel parameters to detect change in the dynamic behavior of the simulation. CUSUM charts on Fourier magnitudes can detect such transitions, and preliminary results suggest that in some cases detection can be more rapid than for CUSUM charts based on queue length.

AB - We examine the use of the Fourier transform to discriminate dynamic behavior differences between congested and uncongested systems. Simulation continuous time statistic 'trajectories' are converted to time series for Fourier analysis. The pattern of Fourier component magnitudes across frequencies differs for congested versus uncongested systems. We use this knowledge to explore statistical process control methods to monitor nonstationary systems for transition from uncongested to congested state and vice versa. In a sense we are monitoring dynamic metamodel parameters to detect change in the dynamic behavior of the simulation. CUSUM charts on Fourier magnitudes can detect such transitions, and preliminary results suggest that in some cases detection can be more rapid than for CUSUM charts based on queue length.

UR - http://www.scopus.com/inward/record.url?scp=85014179491&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014179491&partnerID=8YFLogxK

U2 - 10.1109/WSC.2016.7822107

DO - 10.1109/WSC.2016.7822107

M3 - Conference contribution

AN - SCOPUS:85014179491

T3 - Proceedings - Winter Simulation Conference

SP - 401

EP - 412

BT - 2016 Winter Simulation Conference

A2 - Roeder, Theresa M.

A2 - Frazier, Peter I.

A2 - Szechtman, Robert

A2 - Zhou, Enlu

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Wu X, Barton RR. Fourier trajectory analysis for identifying system congestion. In Roeder TM, Frazier PI, Szechtman R, Zhou E, editors, 2016 Winter Simulation Conference: Simulating Complex Service Systems, WSC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 401-412. 7822107. (Proceedings - Winter Simulation Conference). https://doi.org/10.1109/WSC.2016.7822107