TY - GEN
T1 - Performance Analysis of Computation Offloading in Fog-Radio Access Networks
AU - Xu, Mingfeng
AU - Zhao, Zhongyuan
AU - Peng, Mugen
AU - DIng, Zhiguo
AU - Quek, Tony Q.S.
AU - Bai, Wenle
N1 - Funding Information:
Natural Science Foundation (Grant L182039).
Funding Information:
VI. ACKNOWLEDGMENT This work was supported in part by the National Science and Technology Major Project (Grant 2017ZX03001014), and in part by Beijing Natural Science Foundation (Grant L182039).
Publisher Copyright:
© 2019 IEEE.
PY - 2019/5
Y1 - 2019/5
N2 - In fog-radio access networks (F-RANs), the loadings of backhaul is the bottleneck to fully explore the potential of cloud computing capability, which provide abundant computation resources to execute the computation tasks. In this paper, the performance of computation offloading F-RANs is studied to keep a balance between the tradeoff between the costs and the gains of different computation task processing modes. First, we focus on an opportunistic computation of-(loading strategy in F-RANs, and the computation offloading probability is analyzed based on a stochastic geometry-based model. Second, the computation offloading procedure in F-RANs can be modeled as a Jackson network of queueing system. A closed-form expression of average delay performance is derived, and the global optimal solution of the ratio of computation tasks handled by the cloud computing center is also provided to minimize the average processing delay. Finally, the simulation results are shown to verify the accuracy of analytical results and evaluate the performance gains of hybrid computation offloading in F-RANs.
AB - In fog-radio access networks (F-RANs), the loadings of backhaul is the bottleneck to fully explore the potential of cloud computing capability, which provide abundant computation resources to execute the computation tasks. In this paper, the performance of computation offloading F-RANs is studied to keep a balance between the tradeoff between the costs and the gains of different computation task processing modes. First, we focus on an opportunistic computation of-(loading strategy in F-RANs, and the computation offloading probability is analyzed based on a stochastic geometry-based model. Second, the computation offloading procedure in F-RANs can be modeled as a Jackson network of queueing system. A closed-form expression of average delay performance is derived, and the global optimal solution of the ratio of computation tasks handled by the cloud computing center is also provided to minimize the average processing delay. Finally, the simulation results are shown to verify the accuracy of analytical results and evaluate the performance gains of hybrid computation offloading in F-RANs.
UR - http://www.scopus.com/inward/record.url?scp=85070234294&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85070234294&partnerID=8YFLogxK
U2 - 10.1109/ICC.2019.8761061
DO - 10.1109/ICC.2019.8761061
M3 - Conference contribution
AN - SCOPUS:85070234294
T3 - IEEE International Conference on Communications
BT - 2019 IEEE International Conference on Communications, ICC 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Conference on Communications, ICC 2019
Y2 - 20 May 2019 through 24 May 2019
ER -