Task Replication for Vehicular Cloud: Contextual Combinatorial Bandit with Delayed Feedback

Lixing Chen, Jie Xu

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

Abstract

Vehicular Cloud Computing (VCC) is a new technological shift which exploits the computation and storage resources on vehicles for computational service provisioning. Spare onboard resources are pooled by a VCC operator, e.g. a roadside unit, to serve computational tasks using the vehicle-as-a-resource framework. This paper investigates timely service provisioning for deadline-constrained tasks in VCC systems by leveraging the task replication technique (i.e., allowing one task to be executed by vehicles). A learning-based algorithm, called DATEV (Deadline-Aware Task rEplication for Vehicular Cloud), is proposed to address the special issues in VCC systems including uncertainty of vehicle movements, volatile vehicle members, and large vehicle population. The proposed algorithm is developed based on a novel contextual-combinatorial multi-armed bandit learning framework. DATE-V is ' contextual ' because it utilizes side information (context) of vehicles and tasks to infer the completion probability of a task replication under random vehicle movements. DATE-V is 'combinatorial' because it replicates the received task and sends task replications to multiple vehicles to guarantee the service timeliness. When learning with multi-armed bandit, DATE-V also addresses the practical concern of delayed feedbacks caused by the task transmission/computational delay in using VCC. We rigorously prove that our learning algorithm achieves a sublinear regret bound compared to an oracle algorithm that knows the exact completion probability of any task replications. Simulations are carried out based on real-world vehicle movement traces and the results show that DATE-V significantly outperforms benchmark solutions.

Original languageEnglish (US)
Title of host publicationINFOCOM 2019 - IEEE Conference on Computer Communications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages748-756
Number of pages9
ISBN (Electronic)9781728105154
DOIs
StatePublished - Apr 1 2019
Event2019 IEEE Conference on Computer Communications, INFOCOM 2019 - Paris, France
Duration: Apr 29 2019May 2 2019

Publication series

NameProceedings - IEEE INFOCOM
Volume2019-April
ISSN (Print)0743-166X

Conference

Conference2019 IEEE Conference on Computer Communications, INFOCOM 2019
CountryFrance
CityParis
Period4/29/195/2/19

Fingerprint

Feedback
Cloud computing
Roadsides
Learning algorithms

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Chen, L., & Xu, J. (2019). Task Replication for Vehicular Cloud: Contextual Combinatorial Bandit with Delayed Feedback. In INFOCOM 2019 - IEEE Conference on Computer Communications (pp. 748-756). [8737654] (Proceedings - IEEE INFOCOM; Vol. 2019-April). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INFOCOM.2019.8737654

Task Replication for Vehicular Cloud : Contextual Combinatorial Bandit with Delayed Feedback. / Chen, Lixing; Xu, Jie.

INFOCOM 2019 - IEEE Conference on Computer Communications. Institute of Electrical and Electronics Engineers Inc., 2019. p. 748-756 8737654 (Proceedings - IEEE INFOCOM; Vol. 2019-April).

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

Chen, L & Xu, J 2019, Task Replication for Vehicular Cloud: Contextual Combinatorial Bandit with Delayed Feedback. in INFOCOM 2019 - IEEE Conference on Computer Communications., 8737654, Proceedings - IEEE INFOCOM, vol. 2019-April, Institute of Electrical and Electronics Engineers Inc., pp. 748-756, 2019 IEEE Conference on Computer Communications, INFOCOM 2019, Paris, France, 4/29/19. https://doi.org/10.1109/INFOCOM.2019.8737654
Chen L, Xu J. Task Replication for Vehicular Cloud: Contextual Combinatorial Bandit with Delayed Feedback. In INFOCOM 2019 - IEEE Conference on Computer Communications. Institute of Electrical and Electronics Engineers Inc. 2019. p. 748-756. 8737654. (Proceedings - IEEE INFOCOM). https://doi.org/10.1109/INFOCOM.2019.8737654
Chen, Lixing ; Xu, Jie. / Task Replication for Vehicular Cloud : Contextual Combinatorial Bandit with Delayed Feedback. INFOCOM 2019 - IEEE Conference on Computer Communications. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 748-756 (Proceedings - IEEE INFOCOM).
@inproceedings{523f53e292364e52b5932e2e91fffe98,
title = "Task Replication for Vehicular Cloud: Contextual Combinatorial Bandit with Delayed Feedback",
abstract = "Vehicular Cloud Computing (VCC) is a new technological shift which exploits the computation and storage resources on vehicles for computational service provisioning. Spare onboard resources are pooled by a VCC operator, e.g. a roadside unit, to serve computational tasks using the vehicle-as-a-resource framework. This paper investigates timely service provisioning for deadline-constrained tasks in VCC systems by leveraging the task replication technique (i.e., allowing one task to be executed by vehicles). A learning-based algorithm, called DATEV (Deadline-Aware Task rEplication for Vehicular Cloud), is proposed to address the special issues in VCC systems including uncertainty of vehicle movements, volatile vehicle members, and large vehicle population. The proposed algorithm is developed based on a novel contextual-combinatorial multi-armed bandit learning framework. DATE-V is ' contextual ' because it utilizes side information (context) of vehicles and tasks to infer the completion probability of a task replication under random vehicle movements. DATE-V is 'combinatorial' because it replicates the received task and sends task replications to multiple vehicles to guarantee the service timeliness. When learning with multi-armed bandit, DATE-V also addresses the practical concern of delayed feedbacks caused by the task transmission/computational delay in using VCC. We rigorously prove that our learning algorithm achieves a sublinear regret bound compared to an oracle algorithm that knows the exact completion probability of any task replications. Simulations are carried out based on real-world vehicle movement traces and the results show that DATE-V significantly outperforms benchmark solutions.",
author = "Lixing Chen and Jie Xu",
year = "2019",
month = "4",
day = "1",
doi = "10.1109/INFOCOM.2019.8737654",
language = "English (US)",
series = "Proceedings - IEEE INFOCOM",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "748--756",
booktitle = "INFOCOM 2019 - IEEE Conference on Computer Communications",

}

TY - GEN

T1 - Task Replication for Vehicular Cloud

T2 - Contextual Combinatorial Bandit with Delayed Feedback

AU - Chen, Lixing

AU - Xu, Jie

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Vehicular Cloud Computing (VCC) is a new technological shift which exploits the computation and storage resources on vehicles for computational service provisioning. Spare onboard resources are pooled by a VCC operator, e.g. a roadside unit, to serve computational tasks using the vehicle-as-a-resource framework. This paper investigates timely service provisioning for deadline-constrained tasks in VCC systems by leveraging the task replication technique (i.e., allowing one task to be executed by vehicles). A learning-based algorithm, called DATEV (Deadline-Aware Task rEplication for Vehicular Cloud), is proposed to address the special issues in VCC systems including uncertainty of vehicle movements, volatile vehicle members, and large vehicle population. The proposed algorithm is developed based on a novel contextual-combinatorial multi-armed bandit learning framework. DATE-V is ' contextual ' because it utilizes side information (context) of vehicles and tasks to infer the completion probability of a task replication under random vehicle movements. DATE-V is 'combinatorial' because it replicates the received task and sends task replications to multiple vehicles to guarantee the service timeliness. When learning with multi-armed bandit, DATE-V also addresses the practical concern of delayed feedbacks caused by the task transmission/computational delay in using VCC. We rigorously prove that our learning algorithm achieves a sublinear regret bound compared to an oracle algorithm that knows the exact completion probability of any task replications. Simulations are carried out based on real-world vehicle movement traces and the results show that DATE-V significantly outperforms benchmark solutions.

AB - Vehicular Cloud Computing (VCC) is a new technological shift which exploits the computation and storage resources on vehicles for computational service provisioning. Spare onboard resources are pooled by a VCC operator, e.g. a roadside unit, to serve computational tasks using the vehicle-as-a-resource framework. This paper investigates timely service provisioning for deadline-constrained tasks in VCC systems by leveraging the task replication technique (i.e., allowing one task to be executed by vehicles). A learning-based algorithm, called DATEV (Deadline-Aware Task rEplication for Vehicular Cloud), is proposed to address the special issues in VCC systems including uncertainty of vehicle movements, volatile vehicle members, and large vehicle population. The proposed algorithm is developed based on a novel contextual-combinatorial multi-armed bandit learning framework. DATE-V is ' contextual ' because it utilizes side information (context) of vehicles and tasks to infer the completion probability of a task replication under random vehicle movements. DATE-V is 'combinatorial' because it replicates the received task and sends task replications to multiple vehicles to guarantee the service timeliness. When learning with multi-armed bandit, DATE-V also addresses the practical concern of delayed feedbacks caused by the task transmission/computational delay in using VCC. We rigorously prove that our learning algorithm achieves a sublinear regret bound compared to an oracle algorithm that knows the exact completion probability of any task replications. Simulations are carried out based on real-world vehicle movement traces and the results show that DATE-V significantly outperforms benchmark solutions.

UR - http://www.scopus.com/inward/record.url?scp=85068203872&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068203872&partnerID=8YFLogxK

U2 - 10.1109/INFOCOM.2019.8737654

DO - 10.1109/INFOCOM.2019.8737654

M3 - Conference contribution

AN - SCOPUS:85068203872

T3 - Proceedings - IEEE INFOCOM

SP - 748

EP - 756

BT - INFOCOM 2019 - IEEE Conference on Computer Communications

PB - Institute of Electrical and Electronics Engineers Inc.

ER -