D2D-Enabled Collaborative Edge Caching and Processing with Adaptive Mobile Video Streaming

Abbas Mehrabidavoodabadi; Matti Siekkinen; Gazi Gazi Karam Illahi; Antti Ylä-Jääski

doi:10.1109/WoWMoM.2019.8792981

D2D-Enabled Collaborative Edge Caching and Processing with Adaptive Mobile Video Streaming

Abbas Mehrabidavoodabadi, Matti Siekkinen, Gazi Gazi Karam Illahi, Antti Ylä-Jääski

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

225 Downloads (Pure)

Abstract

Multi-access edge computing (MEC) enables placing video content at the edge of a mobile network with the aim of reducing data traffic in the backhaul network. Direct device-to-device (D2D) communication can further alleviate load from the backhaul network. Both MEC and D2D have already been examined by prior work, but their combination applied to adaptive video streaming have not yet been explored in detail. In this paper, we analyze how enabling D2D jointly with edge computing affects the quality of experience (QoE) of video streaming clients and contributes to reducing the backhaul traffic. To this end, we formulate the problem of jointly maximizing the QoE of the clients and minimizing the backhaul traffic and edge processing as an integer non-linear programming (INLP) optimization model and propose a low-complexity algorithm using self-parameterization technique to solve the problem. The main takeaway from simulation results is that enabling D2D with edge computing reduces the backhaul traffic by approximately 18% and edge processing by 30% on average while maintaining roughly the same average video bitrate per client compared to edge computing without D2D. Our results provide a guideline for system designers to judge the effectiveness of enabling D2D into MEC in the next generation of 5G mobile networks.

Original language	English
Title of host publication	IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) 2019
Publisher	IEEE
Pages	1-10
Number of pages	10
ISBN (Electronic)	978-1-7281-0270-2
ISBN (Print)	978-1-7281-0271-9
DOIs	https://doi.org/10.1109/WoWMoM.2019.8792981
Publication status	Published - 12 Aug 2019
MoE publication type	A4 Conference publication
Event	IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks - Duration: 1 Jan 1900 → …

Conference

Conference	IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks
Abbreviated title	WoWMoM
Period	01/01/1900 → …

Access to Document

10.1109/WoWMoM.2019.8792981

SCI_Mehrabi_D2D-enabled.Accepted ManuscriptAccepted author manuscript, 404 KB

Latency-Critical Mobile Multimedia Services and Applications
Siekkinen, M. (Principal investigator), Zhu, C. (Project Member), Ylä-Jääski, A. (Project Member), Xu, J. (Project Member), Kämäräinen, T. (Project Member), Illahi, G. (Project Member) & Mehrabidavoodabadi, A. (Project Member)
01/09/2016 → 31/08/2019
Project: Academy of Finland: Other research funding
PraNA: ProgrAmmable Network & Analytics
Ylä-Jääski, A. (Principal investigator), Siekkinen, M. (Project Member), Debner, A. (Project Member), Mehrabidavoodabadi, A. (Project Member), Dong, J. (Project Member) & Illahi, G. (Project Member)
01/09/2016 → 31/08/2018
Project: Business Finland: Other research funding

Cite this

@inproceedings{4fd7647998c24a7da924b77776f13e97,

title = "D2D-Enabled Collaborative Edge Caching and Processing with Adaptive Mobile Video Streaming",

abstract = "Multi-access edge computing (MEC) enables placing video content at the edge of a mobile network with the aim of reducing data traffic in the backhaul network. Direct device-to-device (D2D) communication can further alleviate load from the backhaul network. Both MEC and D2D have already been examined by prior work, but their combination applied to adaptive video streaming have not yet been explored in detail. In this paper, we analyze how enabling D2D jointly with edge computing affects the quality of experience (QoE) of video streaming clients and contributes to reducing the backhaul traffic. To this end, we formulate the problem of jointly maximizing the QoE of the clients and minimizing the backhaul traffic and edge processing as an integer non-linear programming (INLP) optimization model and propose a low-complexity algorithm using self-parameterization technique to solve the problem. The main takeaway from simulation results is that enabling D2D with edge computing reduces the backhaul traffic by approximately 18% and edge processing by 30% on average while maintaining roughly the same average video bitrate per client compared to edge computing without D2D. Our results provide a guideline for system designers to judge the effectiveness of enabling D2D into MEC in the next generation of 5G mobile networks.",

author = "Abbas Mehrabidavoodabadi and Matti Siekkinen and {Gazi Karam Illahi}, Gazi and Antti Yl{\"a}-J{\"a}{\"a}ski",

year = "2019",

month = aug,

day = "12",

doi = "10.1109/WoWMoM.2019.8792981",

language = "English",

isbn = "978-1-7281-0271-9",

pages = "1--10",

booktitle = "IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) 2019",

publisher = "IEEE",

address = "United States",

note = "IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, WoWMoM ; Conference date: 01-01-1900",

}

Mehrabidavoodabadi, A, Siekkinen, M, Gazi Karam Illahi, G & Ylä-Jääski, A 2019, D2D-Enabled Collaborative Edge Caching and Processing with Adaptive Mobile Video Streaming. in IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) 2019. IEEE, pp. 1-10, IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, 01/01/1900. https://doi.org/10.1109/WoWMoM.2019.8792981

D2D-Enabled Collaborative Edge Caching and Processing with Adaptive Mobile Video Streaming. / Mehrabidavoodabadi, Abbas; Siekkinen, Matti; Gazi Karam Illahi, Gazi et al.
IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) 2019. IEEE, 2019. p. 1-10.

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

TY - GEN

T1 - D2D-Enabled Collaborative Edge Caching and Processing with Adaptive Mobile Video Streaming

AU - Mehrabidavoodabadi, Abbas

AU - Siekkinen, Matti

AU - Gazi Karam Illahi, Gazi

AU - Ylä-Jääski, Antti

PY - 2019/8/12

Y1 - 2019/8/12

N2 - Multi-access edge computing (MEC) enables placing video content at the edge of a mobile network with the aim of reducing data traffic in the backhaul network. Direct device-to-device (D2D) communication can further alleviate load from the backhaul network. Both MEC and D2D have already been examined by prior work, but their combination applied to adaptive video streaming have not yet been explored in detail. In this paper, we analyze how enabling D2D jointly with edge computing affects the quality of experience (QoE) of video streaming clients and contributes to reducing the backhaul traffic. To this end, we formulate the problem of jointly maximizing the QoE of the clients and minimizing the backhaul traffic and edge processing as an integer non-linear programming (INLP) optimization model and propose a low-complexity algorithm using self-parameterization technique to solve the problem. The main takeaway from simulation results is that enabling D2D with edge computing reduces the backhaul traffic by approximately 18% and edge processing by 30% on average while maintaining roughly the same average video bitrate per client compared to edge computing without D2D. Our results provide a guideline for system designers to judge the effectiveness of enabling D2D into MEC in the next generation of 5G mobile networks.

AB - Multi-access edge computing (MEC) enables placing video content at the edge of a mobile network with the aim of reducing data traffic in the backhaul network. Direct device-to-device (D2D) communication can further alleviate load from the backhaul network. Both MEC and D2D have already been examined by prior work, but their combination applied to adaptive video streaming have not yet been explored in detail. In this paper, we analyze how enabling D2D jointly with edge computing affects the quality of experience (QoE) of video streaming clients and contributes to reducing the backhaul traffic. To this end, we formulate the problem of jointly maximizing the QoE of the clients and minimizing the backhaul traffic and edge processing as an integer non-linear programming (INLP) optimization model and propose a low-complexity algorithm using self-parameterization technique to solve the problem. The main takeaway from simulation results is that enabling D2D with edge computing reduces the backhaul traffic by approximately 18% and edge processing by 30% on average while maintaining roughly the same average video bitrate per client compared to edge computing without D2D. Our results provide a guideline for system designers to judge the effectiveness of enabling D2D into MEC in the next generation of 5G mobile networks.

U2 - 10.1109/WoWMoM.2019.8792981

DO - 10.1109/WoWMoM.2019.8792981

M3 - Conference article in proceedings

SN - 978-1-7281-0271-9

SP - 1

EP - 10

BT - IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) 2019

PB - IEEE

T2 - IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks

Y2 - 1 January 1900

ER -

D2D-Enabled Collaborative Edge Caching and Processing with Adaptive Mobile Video Streaming

Abstract

Conference

Access to Document

Fingerprint

Projects

Latency-Critical Mobile Multimedia Services and Applications

PraNA: ProgrAmmable Network & Analytics

Cite this