Surrogate-assisted high-dimensional optimization on microscopic traffic simulators

Bernhard Werth; Erik Pitzer; Gerald Ostermayer; Michael Affenzeller

Surrogate-assisted high-dimensional optimization on microscopic traffic simulators

Bernhard Werth, Erik Pitzer, Gerald Ostermayer, Michael Affenzeller

Research output: Chapter in Book/Report/Conference proceedings › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Microscopic traffic simulation is able to capture many details of a traffic system, which makes it inherently interesting for simulation-based optimization. However, the considerable computational effort required for a single simulation run limits the use of standard heuristic optimization techniques and encourages the use of surrogate models to facilitate the search for an optimal solution. In this work, a grey-box surrogate model for microscopic traffic simulations is presented which allows the optimization of high-dimensional traffic optimization problems without relying on geographic or simulation-specific knowledge.

Original language	English
Title of host publication	30th European Modeling and Simulation Symposium, EMSS 2018
Editors	Yuri Merkuryev, Miquel Angel Piera, Francesco Longo, Agostino G. Bruzzone, Michael Affenzeller, Emilio Jimenez
Publisher	DIME UNIVERSITY OF GENOA
Pages	46-53
Number of pages	8
ISBN (Electronic)	9788885741065
ISBN (Print)	978-88-85741-03-4
Publication status	Published - 2018
Event	30th European Modeling and Simulation Symposium, EMSS 2018 - Budapest, Hungary Duration: 17 Sept 2018 → 19 Sept 2018

Publication series

Name	30th European Modeling and Simulation Symposium, EMSS 2018

Conference

Conference	30th European Modeling and Simulation Symposium, EMSS 2018
Country/Territory	Hungary
City	Budapest
Period	17.09.2018 → 19.09.2018

Keywords

Evolutionary algorithms
Noisy optimization
Surrogate assisted optimization
Traffic simulation

Cite this

Werth, B., Pitzer, E., Ostermayer, G., & Affenzeller, M. (2018). Surrogate-assisted high-dimensional optimization on microscopic traffic simulators. In Y. Merkuryev, M. A. Piera, F. Longo, A. G. Bruzzone, M. Affenzeller, & E. Jimenez (Eds.), 30th European Modeling and Simulation Symposium, EMSS 2018 (pp. 46-53). (30th European Modeling and Simulation Symposium, EMSS 2018). DIME UNIVERSITY OF GENOA.

Werth, Bernhard ; Pitzer, Erik ; Ostermayer, Gerald et al. / Surrogate-assisted high-dimensional optimization on microscopic traffic simulators. 30th European Modeling and Simulation Symposium, EMSS 2018. editor / Yuri Merkuryev ; Miquel Angel Piera ; Francesco Longo ; Agostino G. Bruzzone ; Michael Affenzeller ; Emilio Jimenez. DIME UNIVERSITY OF GENOA, 2018. pp. 46-53 (30th European Modeling and Simulation Symposium, EMSS 2018).

@inproceedings{9bfbd28a05c54f26b2294f29e63d132e,

title = "Surrogate-assisted high-dimensional optimization on microscopic traffic simulators",

abstract = "Microscopic traffic simulation is able to capture many details of a traffic system, which makes it inherently interesting for simulation-based optimization. However, the considerable computational effort required for a single simulation run limits the use of standard heuristic optimization techniques and encourages the use of surrogate models to facilitate the search for an optimal solution. In this work, a grey-box surrogate model for microscopic traffic simulations is presented which allows the optimization of high-dimensional traffic optimization problems without relying on geographic or simulation-specific knowledge.",

keywords = "Evolutionary algorithms, Noisy optimization, Surrogate assisted optimization, Traffic simulation",

author = "Bernhard Werth and Erik Pitzer and Gerald Ostermayer and Michael Affenzeller",

note = "Publisher Copyright: {\textcopyright} Institute of Information Science. All rights reserved. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.; 30th European Modeling and Simulation Symposium, EMSS 2018 ; Conference date: 17-09-2018 Through 19-09-2018",

year = "2018",

language = "English",

isbn = "978-88-85741-03-4",

series = "30th European Modeling and Simulation Symposium, EMSS 2018",

publisher = "DIME UNIVERSITY OF GENOA",

pages = "46--53",

editor = "Yuri Merkuryev and Piera, {Miquel Angel} and Francesco Longo and Bruzzone, {Agostino G.} and Michael Affenzeller and Emilio Jimenez",

booktitle = "30th European Modeling and Simulation Symposium, EMSS 2018",

}

Werth, B , Pitzer, E , Ostermayer, G & Affenzeller, M 2018, Surrogate-assisted high-dimensional optimization on microscopic traffic simulators. in Y Merkuryev, MA Piera, F Longo, AG Bruzzone, M Affenzeller & E Jimenez (eds), 30th European Modeling and Simulation Symposium, EMSS 2018. 30th European Modeling and Simulation Symposium, EMSS 2018, DIME UNIVERSITY OF GENOA, pp. 46-53, 30th European Modeling and Simulation Symposium, EMSS 2018, Budapest, Hungary, 17.09.2018.

Surrogate-assisted high-dimensional optimization on microscopic traffic simulators. / Werth, Bernhard ; Pitzer, Erik ; Ostermayer, Gerald et al.
30th European Modeling and Simulation Symposium, EMSS 2018. ed. / Yuri Merkuryev; Miquel Angel Piera; Francesco Longo; Agostino G. Bruzzone; Michael Affenzeller; Emilio Jimenez. DIME UNIVERSITY OF GENOA, 2018. p. 46-53 (30th European Modeling and Simulation Symposium, EMSS 2018).

Research output: Chapter in Book/Report/Conference proceedings › Conference contribution › peer-review

TY - GEN

T1 - Surrogate-assisted high-dimensional optimization on microscopic traffic simulators

AU - Werth, Bernhard

AU - Pitzer, Erik

AU - Ostermayer, Gerald

AU - Affenzeller, Michael

PY - 2018

Y1 - 2018

N2 - Microscopic traffic simulation is able to capture many details of a traffic system, which makes it inherently interesting for simulation-based optimization. However, the considerable computational effort required for a single simulation run limits the use of standard heuristic optimization techniques and encourages the use of surrogate models to facilitate the search for an optimal solution. In this work, a grey-box surrogate model for microscopic traffic simulations is presented which allows the optimization of high-dimensional traffic optimization problems without relying on geographic or simulation-specific knowledge.

AB - Microscopic traffic simulation is able to capture many details of a traffic system, which makes it inherently interesting for simulation-based optimization. However, the considerable computational effort required for a single simulation run limits the use of standard heuristic optimization techniques and encourages the use of surrogate models to facilitate the search for an optimal solution. In this work, a grey-box surrogate model for microscopic traffic simulations is presented which allows the optimization of high-dimensional traffic optimization problems without relying on geographic or simulation-specific knowledge.

KW - Evolutionary algorithms

KW - Noisy optimization

KW - Surrogate assisted optimization

KW - Traffic simulation

UR - http://www.scopus.com/inward/record.url?scp=85056746126&partnerID=8YFLogxK

M3 - Conference contribution

SN - 978-88-85741-03-4

T3 - 30th European Modeling and Simulation Symposium, EMSS 2018

SP - 46

EP - 53

BT - 30th European Modeling and Simulation Symposium, EMSS 2018

A2 - Merkuryev, Yuri

A2 - Piera, Miquel Angel

A2 - Longo, Francesco

A2 - Bruzzone, Agostino G.

A2 - Affenzeller, Michael

A2 - Jimenez, Emilio

PB - DIME UNIVERSITY OF GENOA

T2 - 30th European Modeling and Simulation Symposium, EMSS 2018

Y2 - 17 September 2018 through 19 September 2018

ER -

Werth B , Pitzer E , Ostermayer G , Affenzeller M. Surrogate-assisted high-dimensional optimization on microscopic traffic simulators. In Merkuryev Y, Piera MA, Longo F, Bruzzone AG, Affenzeller M, Jimenez E, editors, 30th European Modeling and Simulation Symposium, EMSS 2018. DIME UNIVERSITY OF GENOA. 2018. p. 46-53. (30th European Modeling and Simulation Symposium, EMSS 2018).

Surrogate-assisted high-dimensional optimization on microscopic traffic simulators

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this