(POSTER)DNN Task Allocation for Edge-Aided IoT

Wanli Yu; Yanqiu Huang; Ardalan Najafi; Jinming Sun; Yarib Nevarez; Alberto  Garcia-Ortiz

doi:10.1109/DCOSS-IoT58021.2023.00027

(POSTER)DNN Task Allocation for Edge-Aided IoT

Wanli Yu^*, Yanqiu Huang, Ardalan Najafi^*, Jinming Sun^*, Yarib Nevarez, Alberto Garcia-Ortiz

^*Corresponding author for this work

Research output: Contribution to conference › Poster › Academic

12 Downloads (Pure)

Abstract

Task allocation and scheduling methods are essential for edge-aided IoT to efficiently execute emerging computing-intensive deep neural network (DNN) applications. However, existing studies mainly overlook the waiting time of task execution on edge server caused by the limited parallel computing capacity. This work proposes a task allocation and scheduling method termed DNN-TA by considering the edge limitation. It first formulates the problem of task allocation and offloading for minimizing the application execution delay as a non-linear programming problem. It then converts the non-linear problem into a mixed integer linear programming problem with higher dimensions to reduce the complexity. Extensive experimental results demonstrate that the proposed DNN-TA method significantly reduces the average application execution delay.

Original language	English
Pages	92-94
Number of pages	3
DOIs	https://doi.org/10.1109/DCOSS-IoT58021.2023.00027
Publication status	Published - 27 Sept 2023
Event	19th International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023 - Paphos, Cyprus Duration: 19 Jun 2023 → 21 Jun 2023 Conference number: 19 https://dcoss.org/dcoss23/

Conference

Conference	19th International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023
Abbreviated title	DCOSS-IoT 2023
Country/Territory	Cyprus
City	Paphos
Period	19/06/23 → 21/06/23
Internet address	https://dcoss.org/dcoss23/

Keywords

n/a OA procedure
Artificial neural networks
Parallel processing
Programming
Delays
Mixed integer linear programming
Resource management
Processor scheduling

Access to Document

10.1109/DCOSS-IoT58021.2023.00027

Cite this

@conference{43b06b6499544487b8f724a3ff2d76b2,

title = "(POSTER)DNN Task Allocation for Edge-Aided IoT",

abstract = "Task allocation and scheduling methods are essential for edge-aided IoT to efficiently execute emerging computing-intensive deep neural network (DNN) applications. However, existing studies mainly overlook the waiting time of task execution on edge server caused by the limited parallel computing capacity. This work proposes a task allocation and scheduling method termed DNN-TA by considering the edge limitation. It first formulates the problem of task allocation and offloading for minimizing the application execution delay as a non-linear programming problem. It then converts the non-linear problem into a mixed integer linear programming problem with higher dimensions to reduce the complexity. Extensive experimental results demonstrate that the proposed DNN-TA method significantly reduces the average application execution delay.",

keywords = "n/a OA procedure, Artificial neural networks, Parallel processing, Programming, Delays, Mixed integer linear programming, Resource management, Processor scheduling",

author = "Wanli Yu and Yanqiu Huang and Ardalan Najafi and Jinming Sun and Yarib Nevarez and Alberto Garcia-Ortiz",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023, DCOSS-IoT 2023 ; Conference date: 19-06-2023 Through 21-06-2023",

year = "2023",

month = sep,

day = "27",

doi = "10.1109/DCOSS-IoT58021.2023.00027",

language = "English",

pages = "92--94",

url = "https://dcoss.org/dcoss23/",

}

TY - CONF

T1 - (POSTER)DNN Task Allocation for Edge-Aided IoT

AU - Yu, Wanli

AU - Huang, Yanqiu

AU - Najafi, Ardalan

AU - Sun, Jinming

AU - Nevarez, Yarib

AU - Garcia-Ortiz, Alberto

N1 - Conference code: 19

PY - 2023/9/27

Y1 - 2023/9/27

N2 - Task allocation and scheduling methods are essential for edge-aided IoT to efficiently execute emerging computing-intensive deep neural network (DNN) applications. However, existing studies mainly overlook the waiting time of task execution on edge server caused by the limited parallel computing capacity. This work proposes a task allocation and scheduling method termed DNN-TA by considering the edge limitation. It first formulates the problem of task allocation and offloading for minimizing the application execution delay as a non-linear programming problem. It then converts the non-linear problem into a mixed integer linear programming problem with higher dimensions to reduce the complexity. Extensive experimental results demonstrate that the proposed DNN-TA method significantly reduces the average application execution delay.

AB - Task allocation and scheduling methods are essential for edge-aided IoT to efficiently execute emerging computing-intensive deep neural network (DNN) applications. However, existing studies mainly overlook the waiting time of task execution on edge server caused by the limited parallel computing capacity. This work proposes a task allocation and scheduling method termed DNN-TA by considering the edge limitation. It first formulates the problem of task allocation and offloading for minimizing the application execution delay as a non-linear programming problem. It then converts the non-linear problem into a mixed integer linear programming problem with higher dimensions to reduce the complexity. Extensive experimental results demonstrate that the proposed DNN-TA method significantly reduces the average application execution delay.

KW - n/a OA procedure

KW - Artificial neural networks

KW - Parallel processing

KW - Programming

KW - Delays

KW - Mixed integer linear programming

KW - Resource management

KW - Processor scheduling

UR - http://www.scopus.com/inward/record.url?scp=85174405581&partnerID=8YFLogxK

U2 - 10.1109/DCOSS-IoT58021.2023.00027

DO - 10.1109/DCOSS-IoT58021.2023.00027

M3 - Poster

AN - SCOPUS:85174405581

SP - 92

EP - 94

T2 - 19th International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023

Y2 - 19 June 2023 through 21 June 2023

ER -

(POSTER)DNN Task Allocation for Edge-Aided IoT

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this