Data‐driven urban traffic model‐free adaptive iterative learning control with traffic data dropout compensation

Data‐driven urban traffic model‐free adaptive iterative learning control with traffic data dropout compensation

Abstract In this paper, to fully utilize the urban traffic flow characteristics of similarity and repeatability without using a mathematical traffic model, a data‐driven urban traffic control strategy based on model‐free adaptive iterative learning control (MFAILC) scheme is put forward. Firstly, by...

Full description

Bibliographic Details
Main Authors: Dai Li, Zhongsheng Hou
Format: Article
Language:English
Published: Wiley 2021-07-01
Series:IET Control Theory & Applications
Online Access:https://doi.org/10.1049/cth2.12141
id doaj-5eb911921f29400594a07b0abf63ed60
record_format Article
spelling doaj-5eb911921f29400594a07b0abf63ed602021-08-19T09:15:33ZengWileyIET Control Theory & Applications1751-86441751-86522021-07-0115111533154410.1049/cth2.12141Data‐driven urban traffic model‐free adaptive iterative learning control with traffic data dropout compensationDai Li0Zhongsheng Hou1Advanced Control Systems Laboratory School of Electronic and Information Engineering Beijing Jiaotong University Beijing ChinaAdvanced Control Systems Laboratory School of Electronic and Information Engineering Beijing Jiaotong University Beijing ChinaAbstract In this paper, to fully utilize the urban traffic flow characteristics of similarity and repeatability without using a mathematical traffic model, a data‐driven urban traffic control strategy based on model‐free adaptive iterative learning control (MFAILC) scheme is put forward. Firstly, by dynamically linearizing the urban traffic dynamics along the iteration axis, the traffic network system is transformed into a MFAILC data model with the help of repetitive pattern of urban traffic flow. Then, the traffic controller is designed based on the derived MFAILC data model only using the I/O data of the traffic network. Finally, a traffic data compensation method is proposed to deal with data dropout problem. Simulation study verifies the feasibility and effectiveness of the proposed control method.https://doi.org/10.1049/cth2.12141
collection DOAJ
language English
format Article
sources DOAJ
author Dai Li
Zhongsheng Hou
spellingShingle Dai Li
Zhongsheng Hou
Data‐driven urban traffic model‐free adaptive iterative learning control with traffic data dropout compensation
IET Control Theory & Applications
author_facet Dai Li
Zhongsheng Hou
author_sort Dai Li
title Data‐driven urban traffic model‐free adaptive iterative learning control with traffic data dropout compensation
title_short Data‐driven urban traffic model‐free adaptive iterative learning control with traffic data dropout compensation
title_full Data‐driven urban traffic model‐free adaptive iterative learning control with traffic data dropout compensation
title_fullStr Data‐driven urban traffic model‐free adaptive iterative learning control with traffic data dropout compensation
title_full_unstemmed Data‐driven urban traffic model‐free adaptive iterative learning control with traffic data dropout compensation
title_sort data‐driven urban traffic model‐free adaptive iterative learning control with traffic data dropout compensation
publisher Wiley
series IET Control Theory & Applications
issn 1751-8644
1751-8652
publishDate 2021-07-01
description Abstract In this paper, to fully utilize the urban traffic flow characteristics of similarity and repeatability without using a mathematical traffic model, a data‐driven urban traffic control strategy based on model‐free adaptive iterative learning control (MFAILC) scheme is put forward. Firstly, by dynamically linearizing the urban traffic dynamics along the iteration axis, the traffic network system is transformed into a MFAILC data model with the help of repetitive pattern of urban traffic flow. Then, the traffic controller is designed based on the derived MFAILC data model only using the I/O data of the traffic network. Finally, a traffic data compensation method is proposed to deal with data dropout problem. Simulation study verifies the feasibility and effectiveness of the proposed control method.
url https://doi.org/10.1049/cth2.12141
work_keys_str_mv AT daili datadrivenurbantrafficmodelfreeadaptiveiterativelearningcontrolwithtrafficdatadropoutcompensation
AT zhongshenghou datadrivenurbantrafficmodelfreeadaptiveiterativelearningcontrolwithtrafficdatadropoutcompensation
_version_ 1721202407361216512

Similar Items