TY - JOUR
T1 - Beef up the Edge
T2 - Spectrum-Aware Placement of Edge Computing Services for the Internet of Things
AU - Ding, Haichuan
AU - Guo, Yuanxiong
AU - Li, Xuanheng
AU - Fang, Yuguang
PY - 2019/12
Y1 - 2019/12
N2 - In this paper, we introduce a network entity called point of connection (PoC), which is equipped with customized powerful communication, computing, and storage (CCS) capabilities, and design a data transportation network (DART) of interconnected PoCs to facilitate the provision of Internet of Things (IoT) services. By exploiting the powerful CCS capabilities of PoCs, DART brings both communication and computing services much closer to end devices so that resource-constrained IoT devices could have access to the desired communication and computing services. To achieve the design goals of DART, we further study the spectrum-aware placement of edge computing services. We formulate the service placement as a stochastic mixed-integer optimization problem and propose an enhanced coarse-grained fixing procedure to facilitate efficient solution finding. Through extensive simulations, we demonstrate the effectiveness of the resulting spectrum-aware service placement strategies and the proposed solution approach.
AB - In this paper, we introduce a network entity called point of connection (PoC), which is equipped with customized powerful communication, computing, and storage (CCS) capabilities, and design a data transportation network (DART) of interconnected PoCs to facilitate the provision of Internet of Things (IoT) services. By exploiting the powerful CCS capabilities of PoCs, DART brings both communication and computing services much closer to end devices so that resource-constrained IoT devices could have access to the desired communication and computing services. To achieve the design goals of DART, we further study the spectrum-aware placement of edge computing services. We formulate the service placement as a stochastic mixed-integer optimization problem and propose an enhanced coarse-grained fixing procedure to facilitate efficient solution finding. Through extensive simulations, we demonstrate the effectiveness of the resulting spectrum-aware service placement strategies and the proposed solution approach.
KW - edge computing
KW - Internet of Things (IoT)
KW - service placement
KW - spectrum allocation
UR - http://www.scopus.com/inward/record.url?scp=85057873858&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85057873858&origin=recordpage
U2 - 10.1109/TMC.2018.2883952
DO - 10.1109/TMC.2018.2883952
M3 - RGC 21 - Publication in refereed journal
SN - 1536-1233
VL - 18
SP - 2783
EP - 2795
JO - IEEE Transactions on Mobile Computing
JF - IEEE Transactions on Mobile Computing
IS - 12
M1 - 8554109
ER -