Distributed and Learning-based Model Predictive Control for Urban Rail Transit Networks

X. Liu

doi:10.4233/uuid:29f865ed-5af2-466e-ba4f-37a4c0b72c65

Distributed and Learning-based Model Predictive Control for Urban Rail Transit Networks

X. Liu

Team Bart De Schutter

Research output: Thesis › Dissertation (TU Delft)

Abstract

Urban rail transit networks are dedicated to providing safe, efficient, and eco-friendly transportation services for passengers. This thesis focuses on innovative model predictive control (MPC) strategies for the integration of passenger flows, timetables, and train speeds in urban rail transit networks. We introduce several innovative MPC frameworks, including bi-level MPC, scenario-based distributed MPC, learning-based MPC, and cooperative distributed MPC. These approaches exhibit significantly improved performance compared to conventional methods.

Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	Delft University of Technology
Supervisors/Advisors	De Schutter, B.H.K., Supervisor Dabiri, A., Advisor
Award date	23 Oct 2024
Print ISBNs	978-90-5584-350-3
Electronic ISBNs	978-94-6384-659-2
DOIs	https://doi.org/10.4233/uuid:29f865ed-5af2-466e-ba4f-37a4c0b72c65
Publication status	Published - 2024

Keywords

Urban Rail Transit Network
Model Predictive Control
Distributed Control
Learning-based Control

Access to Document

10.4233/uuid:29f865ed-5af2-466e-ba4f-37a4c0b72c65

Embargoed Document

Xiaoyu Liu_Thesis_for_lib
Final published version, 6.54 MB
Embargo ends: 23/10/25

Cite this

@phdthesis{29f865ed5af2466eba4f37a4c0b72c65,

title = "Distributed and Learning-based Model Predictive Control for Urban Rail Transit Networks",

abstract = "Urban rail transit networks are dedicated to providing safe, efficient, and eco-friendly transportation services for passengers. This thesis focuses on innovative model predictive control (MPC) strategies for the integration of passenger flows, timetables, and train speeds in urban rail transit networks. We introduce several innovative MPC frameworks, including bi-level MPC, scenario-based distributed MPC, learning-based MPC, and cooperative distributed MPC. These approaches exhibit significantly improved performance compared to conventional methods.",

keywords = "Urban Rail Transit Network, Model Predictive Control, Distributed Control, Learning-based Control",

author = "X. Liu",

year = "2024",

doi = "10.4233/uuid:29f865ed-5af2-466e-ba4f-37a4c0b72c65",

language = "English",

isbn = "978-90-5584-350-3",

series = "TRAIL Thesis Series",

number = "T2024/10",

type = "Dissertation (TU Delft)",

school = "Delft University of Technology",

}

TY - THES

T1 - Distributed and Learning-based Model Predictive Control for Urban Rail Transit Networks

AU - Liu, X.

PY - 2024

Y1 - 2024

N2 - Urban rail transit networks are dedicated to providing safe, efficient, and eco-friendly transportation services for passengers. This thesis focuses on innovative model predictive control (MPC) strategies for the integration of passenger flows, timetables, and train speeds in urban rail transit networks. We introduce several innovative MPC frameworks, including bi-level MPC, scenario-based distributed MPC, learning-based MPC, and cooperative distributed MPC. These approaches exhibit significantly improved performance compared to conventional methods.

AB - Urban rail transit networks are dedicated to providing safe, efficient, and eco-friendly transportation services for passengers. This thesis focuses on innovative model predictive control (MPC) strategies for the integration of passenger flows, timetables, and train speeds in urban rail transit networks. We introduce several innovative MPC frameworks, including bi-level MPC, scenario-based distributed MPC, learning-based MPC, and cooperative distributed MPC. These approaches exhibit significantly improved performance compared to conventional methods.

KW - Urban Rail Transit Network

KW - Model Predictive Control

KW - Distributed Control

KW - Learning-based Control

U2 - 10.4233/uuid:29f865ed-5af2-466e-ba4f-37a4c0b72c65

DO - 10.4233/uuid:29f865ed-5af2-466e-ba4f-37a4c0b72c65

M3 - Dissertation (TU Delft)

SN - 978-90-5584-350-3

T3 - TRAIL Thesis Series

ER -

Distributed and Learning-based Model Predictive Control for Urban Rail Transit Networks

Abstract

Keywords

Access to Document

Embargoed Document

Fingerprint

Cite this