Joint optimization of energy and delay for computation offloading in cloudlet-assisted mobile cloud computing
- 31 Downloads
In the mobile cloud computing (MCC), although offloading requests to the distant central cloud or nearby cloudlet can reduce energy consumption at the mobile devices (MDs), it may also incur a large execution delay including transmission time from the MDs to the servers and waiting time at the servers. Therefore, how to balance the energy consumption and delay performance is of great research importance. In this paper, we bring a thorough study on the energy consumption and execution delay of offloading process in a cloudlet-assisted MCC. Specifically, heterogeneity of request executions are explicitly considered. When there is a small cell base station (SBS) available, the MDs can connect with cloudlet via the SBS and if only a macro cell base station is available, the MD can connect with the central cloud through it. We derive the analytic results of the energy consumption and execution delay performance with the assumption of three different queue models at the MD, cloudlet and central cloud. Based on the theoretical analysis, the multi-objective optimization problems are formulated with the joint objectives to minimize the energy consumption and delay by finding the optimal offloading probability. The simulation results demonstrate the effectiveness of the proposed scheme.
KeywordsEnergy consumption Execution delay Local execution Offloading probability Cloudlet-assistant MCC
This work is partly supported by the Academy of Finland (Decision No. 284748) and Hebei NSFC (F2016203383).
- 10.Zanni, A., Yu, S. Y., Bellavista, P., Langar, R., & Secci, S. (2017). Automated selection of offloadable tasks for mobile computation offloading in edge computing. In 2017 13th international conference on network and service management (CNSM) (pp. 1–5).Google Scholar
- 11.Zanni, A., Yu, S. Y., Secci, S., Langar, R., Bellavista, P., & Macedo, D. F. (2017). Automated offloading of android applications for computation/energy optimizations. In 2017 IEEE conference on computer communications workshops (INFOCOM WKSHPS) (pp. 990–991).Google Scholar