TY - GEN
T1 - An improved sierpinski fractal based network architecture for edge computing datacenters
AU - Qi, Han
AU - Li, Zelin
AU - Qi, Jian
AU - Wang, Xinyao
AU - Gani, Abdullah
AU - Whaiduzzaman, Md
N1 - Funding Information:
This work is funded by the Scientific Research Foundation for Advanced Talents from Shenyang Aerospace University - 18YB06.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - Edge computing (EC) aims to place partial processing resources at the edge datacenters (EDCs) for terminal devices to improve the delivery of content and applications to end users. Compared with traditional centralized cloud datacenters (CDC), the EDCs are distributed on the edge of the network that closer to terminal devices in geographical location for reducing the delay of data transmission between cloud and terminals, and enhancing the quality of services for the time sensitive applications. Currently, the edge datacenter networks (EDCNs) use the tree-hierarchical architecture which inherits the problems of limited bandwidth capacity and lower server utilization. This requires a new design of scalable and inexpensive EDCN infrastructure which enables high-speed interconnection for exponentially increasing number of terminal devices and provides fault-tolerant and high network capacity. In this paper, we propose a novel architecture call Sierpinski Triangle Based (STB) for EDCN which uses Sierpinski fractal to mitigate throughput bottleneck in aggregate layers as accumulated in tree hierarchical architecture. The results of the experiment show that the STB architecture has higher throughput than both traditional tree-hierarchical and DCell architectures from the scale of 12 to 363 servers without link failure happens.
AB - Edge computing (EC) aims to place partial processing resources at the edge datacenters (EDCs) for terminal devices to improve the delivery of content and applications to end users. Compared with traditional centralized cloud datacenters (CDC), the EDCs are distributed on the edge of the network that closer to terminal devices in geographical location for reducing the delay of data transmission between cloud and terminals, and enhancing the quality of services for the time sensitive applications. Currently, the edge datacenter networks (EDCNs) use the tree-hierarchical architecture which inherits the problems of limited bandwidth capacity and lower server utilization. This requires a new design of scalable and inexpensive EDCN infrastructure which enables high-speed interconnection for exponentially increasing number of terminal devices and provides fault-tolerant and high network capacity. In this paper, we propose a novel architecture call Sierpinski Triangle Based (STB) for EDCN which uses Sierpinski fractal to mitigate throughput bottleneck in aggregate layers as accumulated in tree hierarchical architecture. The results of the experiment show that the STB architecture has higher throughput than both traditional tree-hierarchical and DCell architectures from the scale of 12 to 363 servers without link failure happens.
KW - Architecture
KW - Edge computing
KW - Edge datacenter network
KW - Network topology
UR - http://www.scopus.com/inward/record.url?scp=85081104733&partnerID=8YFLogxK
U2 - 10.1109/IUCC/DSCI/SmartCNS.2019.00034
DO - 10.1109/IUCC/DSCI/SmartCNS.2019.00034
M3 - Conference contribution
AN - SCOPUS:85081104733
T3 - Proceedings - 2019 IEEE International Conferences on Ubiquitous Computing and Communications and Data Science and Computational Intelligence and Smart Computing, Networking and Services, IUCC/DSCI/SmartCNS 2019
SP - 27
EP - 34
BT - Proceedings - 2019 IEEE International Conferences on Ubiquitous Computing and Communications and Data Science and Computational Intelligence and Smart Computing, Networking and Services, IUCC/DSCI/SmartCNS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Conferences on Ubiquitous Computing and Communications and Data Science and Computational Intelligence and Smart Computing, Networking and Services, IUCC/DSCI/SmartCNS 2019
Y2 - 21 October 2019 through 23 October 2019
ER -