Time-Adaptive and Cognitive Cloud Offloading Using Multiple Radios
While the problem setup in the previous chapter is the most general, the solution presented in the previous chapter could be computationally expensive. This chapter introduces more practical heuristic time-adaptive schemes to schedule the components for offloading, while simultaneously optimizing the percentages of data to be sent by the mobile and the cloud via each wireless interface. A comprehensive model for the utility function is described that trades-off resources saved by remote execution (such as energy, memory, and CPU consumption by the mobile device) with the cost of communication required for offloading (such as energy consumed by offloading and the data queue length at the multiple radio interfaces). Two different ways to implement the solution are discussed.
The offloading strategies for transmission at the mobile and cloud end use past wireless interface data, queue status, and the current data flow to update the current queue status.
- 7.B.-G. Chun, P. Maniatis, Augmented smartphone applications through clone cloud execution, in Proceedings of the Conference on Hot Topics in Operating Systems, HotOS’09 (2009), pp. 8–8Google Scholar
- 30.J. Liu, B. Priyantha, T. Hart, H.S. Ramos, A.A.F. Loureiro, Q. Wang, Energy efficient GPS sensing with cloud offloading, in Proceedings of the ACM Conference on Embedded Network Sensor Systems, SenSys ’12 (2012)Google Scholar