On Scaling Property of Information-Centric Networking

Ryo NAKAMURA; Hiroyuki OHSAKI

doi:10.1587/transcom.2018EIP0005

On Scaling Property of Information-Centric Networking

Ryo NAKAMURA, Hiroyuki OHSAKI

Full Text Views

0

Cite this

Summary :

In this paper, we focus on a large-scale ICN (Information-Centric Networking), and reveal the scaling property of ICN. Because of in-network content caching, ICN is a sort of cache networks and expected to be a promising architecture for replacing future Internet. To realize a global-scale (e.g., Internet-scale) ICN, it is crucial to understand the fundamental properties of such large-scale cache networks. However, the scaling property of ICN has not been well understood due to the lack of theoretical foundations and analysis methodologies. For answering research questions regarding the scaling property of ICN, we derive the cache hit probability at each router, the average content delivery delay of each entity, and the average content delivery delay of all entities over a content distribution tree comprised of a single repository (i.e., content provider), multiple routers, and multiple entities (i.e., content consumers). Through several numerical examples, we investigate the effect of the topology and the size of the content distribution tree and the cache size at routers on the average content delivery delay of all entities. Our findings include that the average content delivery delay of ICNs converges to a constant value if the cache size of routers are not small, which implies high scalability of ICNs, and that even when the network size would grow indefinitely, the average content delivery delay is upper-bounded by a constant value if routers in the network are provided with a fair amount of content caches.

Publication: IEICE TRANSACTIONS on Communications Vol.E102-B No.9 pp.1804-1812

Publication Date: 2019/09/01

Publicized: 2019/03/22

Online ISSN: 1745-1345

DOI: 10.1587/transcom.2018EIP0005

Type of Manuscript: Special Section PAPER (Special Section on Enhancing Information Centric Networking Technologies Towards Real-world Infrastructure)

Category

Authors

Ryo NAKAMURA
Kwansei Gakuin University
Hiroyuki OHSAKI
Kwansei Gakuin University

Keyword

ICN (information-centric networking), large-scale network, cache network, content delivery delay, cache hit probability

Cite this

Copy

Ryo NAKAMURA, Hiroyuki OHSAKI, "On Scaling Property of Information-Centric Networking" in IEICE TRANSACTIONS on Communications, vol. E102-B, no. 9, pp. 1804-1812, September 2019, doi: 10.1587/transcom.2018EIP0005.
Abstract: In this paper, we focus on a large-scale ICN (Information-Centric Networking), and reveal the scaling property of ICN. Because of in-network content caching, ICN is a sort of cache networks and expected to be a promising architecture for replacing future Internet. To realize a global-scale (e.g., Internet-scale) ICN, it is crucial to understand the fundamental properties of such large-scale cache networks. However, the scaling property of ICN has not been well understood due to the lack of theoretical foundations and analysis methodologies. For answering research questions regarding the scaling property of ICN, we derive the cache hit probability at each router, the average content delivery delay of each entity, and the average content delivery delay of all entities over a content distribution tree comprised of a single repository (i.e., content provider), multiple routers, and multiple entities (i.e., content consumers). Through several numerical examples, we investigate the effect of the topology and the size of the content distribution tree and the cache size at routers on the average content delivery delay of all entities. Our findings include that the average content delivery delay of ICNs converges to a constant value if the cache size of routers are not small, which implies high scalability of ICNs, and that even when the network size would grow indefinitely, the average content delivery delay is upper-bounded by a constant value if routers in the network are provided with a fair amount of content caches.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2018EIP0005/_p

Copy

@ARTICLE{e102-b_9_1804,
author={Ryo NAKAMURA, Hiroyuki OHSAKI, },
journal={IEICE TRANSACTIONS on Communications},
title={On Scaling Property of Information-Centric Networking},
year={2019},
volume={E102-B},
number={9},
pages={1804-1812},
abstract={In this paper, we focus on a large-scale ICN (Information-Centric Networking), and reveal the scaling property of ICN. Because of in-network content caching, ICN is a sort of cache networks and expected to be a promising architecture for replacing future Internet. To realize a global-scale (e.g., Internet-scale) ICN, it is crucial to understand the fundamental properties of such large-scale cache networks. However, the scaling property of ICN has not been well understood due to the lack of theoretical foundations and analysis methodologies. For answering research questions regarding the scaling property of ICN, we derive the cache hit probability at each router, the average content delivery delay of each entity, and the average content delivery delay of all entities over a content distribution tree comprised of a single repository (i.e., content provider), multiple routers, and multiple entities (i.e., content consumers). Through several numerical examples, we investigate the effect of the topology and the size of the content distribution tree and the cache size at routers on the average content delivery delay of all entities. Our findings include that the average content delivery delay of ICNs converges to a constant value if the cache size of routers are not small, which implies high scalability of ICNs, and that even when the network size would grow indefinitely, the average content delivery delay is upper-bounded by a constant value if routers in the network are provided with a fair amount of content caches.},
keywords={},
doi={10.1587/transcom.2018EIP0005},
ISSN={1745-1345},
month={September},}

Copy

TY - JOUR
TI - On Scaling Property of Information-Centric Networking
T2 - IEICE TRANSACTIONS on Communications
SP - 1804
EP - 1812
AU - Ryo NAKAMURA
AU - Hiroyuki OHSAKI
PY - 2019
DO - 10.1587/transcom.2018EIP0005
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E102-B
IS - 9
JA - IEICE TRANSACTIONS on Communications
Y1 - September 2019
AB - In this paper, we focus on a large-scale ICN (Information-Centric Networking), and reveal the scaling property of ICN. Because of in-network content caching, ICN is a sort of cache networks and expected to be a promising architecture for replacing future Internet. To realize a global-scale (e.g., Internet-scale) ICN, it is crucial to understand the fundamental properties of such large-scale cache networks. However, the scaling property of ICN has not been well understood due to the lack of theoretical foundations and analysis methodologies. For answering research questions regarding the scaling property of ICN, we derive the cache hit probability at each router, the average content delivery delay of each entity, and the average content delivery delay of all entities over a content distribution tree comprised of a single repository (i.e., content provider), multiple routers, and multiple entities (i.e., content consumers). Through several numerical examples, we investigate the effect of the topology and the size of the content distribution tree and the cache size at routers on the average content delivery delay of all entities. Our findings include that the average content delivery delay of ICNs converges to a constant value if the cache size of routers are not small, which implies high scalability of ICNs, and that even when the network size would grow indefinitely, the average content delivery delay is upper-bounded by a constant value if routers in the network are provided with a fair amount of content caches.
ER -