In-Network Dynamic Compute Orchestration over Mobile Edge Systems

Roman Kovalchukov; Roman Glazkov; Srikathyayani Srikanteswara; Yi Zhang; Dmitri Moltchanov; Gabriel Arrobo; Hao Feng; Marcin Spoczynski; Nageen Himayat

doi:10.1109/VTC2023-Spring57618.2023.10200992

In-Network Dynamic Compute Orchestration over Mobile Edge Systems

Roman Kovalchukov^*
, Roman Glazkov
, Srikathyayani Srikanteswara
, Yi Zhang
, Dmitri Moltchanov
, Gabriel Arrobo
, Hao Feng
, Marcin Spoczynski
, Nageen Himayat

^*Corresponding author for this work

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

1 Citation (Scopus)

27 Downloads (Pure)

Abstract

In this paper, we propose a new service orchestration approach for in-network fully distributed dynamic compute composition with limited involvement from the consumer and no centralized coordinator. The service is composed fully inside the network including assembling data and software, and compute node selection, leveraging standardized NDN functionalities. The use of the proposed approach will enable smooth support of dynamic compute services over wireless/mobile edge and edge/fog NDN-based systems, where the use of conventional IP approach faces fundamental difficulties related to dynamic allocation of IP addresses. We will also outline extensions of the proposed approach for streaming data, function chaining and re-use of partially computed results. Our numerical results show that the proposed method improves service reliability at the edge by increasing the Interest satisfaction by 5-10 times depending on the considered deployment, network topology, and resources.

Original language	English
Title of host publication	2023 IEEE 97th Vehicular Technology Conference, VTC 2023-Spring - Proceedings
Publisher	IEEE
ISBN (Electronic)	979-8-3503-1114-3
DOIs	https://doi.org/10.1109/VTC2023-Spring57618.2023.10200992
Publication status	Published - 2023
Publication type	A4 Article in conference proceedings
Event	IEEE Vehicular Technology Conference - Florence, Italy Duration: 20 Jun 2023 → 23 Jun 2023 Conference number: 97

Publication series

Name	IEEE Vehicular Technology Conference
ISSN (Print)	1090-3038
ISSN (Electronic)	2577-2465

Conference

Conference	IEEE Vehicular Technology Conference
Country/Territory	Italy
City	Florence
Period	20/06/23 → 23/06/23

Keywords

Dynamic edge computing
function chaining
in-network service orchestration
named data networking

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Computer Science Applications
Electrical and Electronic Engineering
Applied Mathematics

Access to Document

10.1109/VTC2023-Spring57618.2023.10200992

In-Network Dynamic Compute Orchestration
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Accepted author manuscript, 976 KBLicence: Unspecified

https://urn.fi/URN:NBN:fi:tuni-202309268469Licence: Unspecified

Cite this

Kovalchukov, R., Glazkov, R., Srikanteswara, S., Zhang, Y., Moltchanov, D., Arrobo, G., Feng, H., Spoczynski, M., & Himayat, N. (2023). In-Network Dynamic Compute Orchestration over Mobile Edge Systems. In 2023 IEEE 97th Vehicular Technology Conference, VTC 2023-Spring - Proceedings (IEEE Vehicular Technology Conference). IEEE. https://doi.org/10.1109/VTC2023-Spring57618.2023.10200992

@inproceedings{4b191f23f6fd444bac2099b7f9dc7272,

title = "In-Network Dynamic Compute Orchestration over Mobile Edge Systems",

abstract = "In this paper, we propose a new service orchestration approach for in-network fully distributed dynamic compute composition with limited involvement from the consumer and no centralized coordinator. The service is composed fully inside the network including assembling data and software, and compute node selection, leveraging standardized NDN functionalities. The use of the proposed approach will enable smooth support of dynamic compute services over wireless/mobile edge and edge/fog NDN-based systems, where the use of conventional IP approach faces fundamental difficulties related to dynamic allocation of IP addresses. We will also outline extensions of the proposed approach for streaming data, function chaining and re-use of partially computed results. Our numerical results show that the proposed method improves service reliability at the edge by increasing the Interest satisfaction by 5-10 times depending on the considered deployment, network topology, and resources.",

keywords = "Dynamic edge computing, function chaining, in-network service orchestration, named data networking",

author = "Roman Kovalchukov and Roman Glazkov and Srikathyayani Srikanteswara and Yi Zhang and Dmitri Moltchanov and Gabriel Arrobo and Hao Feng and Marcin Spoczynski and Nageen Himayat",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; IEEE Vehicular Technology Conference ; Conference date: 20-06-2023 Through 23-06-2023",

year = "2023",

doi = "10.1109/VTC2023-Spring57618.2023.10200992",

language = "English",

series = "IEEE Vehicular Technology Conference",

publisher = "IEEE",

booktitle = "2023 IEEE 97th Vehicular Technology Conference, VTC 2023-Spring - Proceedings",

address = "United States",

}

Kovalchukov, R , Glazkov, R, Srikanteswara, S, Zhang, Y, Moltchanov, D, Arrobo, G, Feng, H, Spoczynski, M & Himayat, N 2023, In-Network Dynamic Compute Orchestration over Mobile Edge Systems. in 2023 IEEE 97th Vehicular Technology Conference, VTC 2023-Spring - Proceedings. IEEE Vehicular Technology Conference, IEEE, IEEE Vehicular Technology Conference, Florence, Italy, 20/06/23. https://doi.org/10.1109/VTC2023-Spring57618.2023.10200992

In-Network Dynamic Compute Orchestration over Mobile Edge Systems. / Kovalchukov, Roman ; Glazkov, Roman; Srikanteswara, Srikathyayani et al.
2023 IEEE 97th Vehicular Technology Conference, VTC 2023-Spring - Proceedings. IEEE, 2023. (IEEE Vehicular Technology Conference).

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

TY - GEN

T1 - In-Network Dynamic Compute Orchestration over Mobile Edge Systems

AU - Kovalchukov, Roman

AU - Glazkov, Roman

AU - Srikanteswara, Srikathyayani

AU - Zhang, Yi

AU - Moltchanov, Dmitri

AU - Arrobo, Gabriel

AU - Feng, Hao

AU - Spoczynski, Marcin

AU - Himayat, Nageen

N1 - Conference code: 97

PY - 2023

Y1 - 2023

N2 - In this paper, we propose a new service orchestration approach for in-network fully distributed dynamic compute composition with limited involvement from the consumer and no centralized coordinator. The service is composed fully inside the network including assembling data and software, and compute node selection, leveraging standardized NDN functionalities. The use of the proposed approach will enable smooth support of dynamic compute services over wireless/mobile edge and edge/fog NDN-based systems, where the use of conventional IP approach faces fundamental difficulties related to dynamic allocation of IP addresses. We will also outline extensions of the proposed approach for streaming data, function chaining and re-use of partially computed results. Our numerical results show that the proposed method improves service reliability at the edge by increasing the Interest satisfaction by 5-10 times depending on the considered deployment, network topology, and resources.

AB - In this paper, we propose a new service orchestration approach for in-network fully distributed dynamic compute composition with limited involvement from the consumer and no centralized coordinator. The service is composed fully inside the network including assembling data and software, and compute node selection, leveraging standardized NDN functionalities. The use of the proposed approach will enable smooth support of dynamic compute services over wireless/mobile edge and edge/fog NDN-based systems, where the use of conventional IP approach faces fundamental difficulties related to dynamic allocation of IP addresses. We will also outline extensions of the proposed approach for streaming data, function chaining and re-use of partially computed results. Our numerical results show that the proposed method improves service reliability at the edge by increasing the Interest satisfaction by 5-10 times depending on the considered deployment, network topology, and resources.

KW - Dynamic edge computing

KW - function chaining

KW - in-network service orchestration

KW - named data networking

U2 - 10.1109/VTC2023-Spring57618.2023.10200992

DO - 10.1109/VTC2023-Spring57618.2023.10200992

M3 - Conference contribution

AN - SCOPUS:85169823088

T3 - IEEE Vehicular Technology Conference

BT - 2023 IEEE 97th Vehicular Technology Conference, VTC 2023-Spring - Proceedings

PB - IEEE

T2 - IEEE Vehicular Technology Conference

Y2 - 20 June 2023 through 23 June 2023

ER -

In-Network Dynamic Compute Orchestration over Mobile Edge Systems

Abstract

Publication series

Conference

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this