Cognitive Cloud Offloading Using Multiple Radios
Given recent advances in technologies that enable bandwidth aggregation in wireless devices and the development of the HetNet, it is possible to simultaneously RAT interfaces in a wireless device. This chapter discusses optimal computational offloading that uses all available and viable RAT interfaces of a mobile device to achieve the best possible resource trade-offs when computationally offloading. The concept of cognitive cloud offloading is introduced. The solution discussed in this chapter optimally decides which components of an application to offload and which to execute locally, while simultaneously optimizing the percentage of data (associated with this offloading) to be sent via each viable radio interface. This chapter also discusses other solutions that fall under the general umbrella of radio-aware computation offloading.
This chapter also discusses a comprehensive model for the energy consumed by the mobile device, including energy expended in communicating relevant data between the cloud and the device. Note that unlike in the previous chapter, the solutions studied in this chapter assume a compiler pre-determined scheduling order for the components of the application.
- 3.S. Boyd, A. Mutapcic, Subgradient methods. Lecture Notes of EE364b, Stanford University, Stanford, CA, Spring Quarter (2008)Google Scholar
- 10.E. Cuervo, A. Balasubramanian, D.-K. Cho, A. Wolman, S. Saroiu, R. Chandra, P. Bahl, MAUI: making smartphones last longer with code offload, in Proceedings of the International Conference on Mobile Systems, Applications, and Services, MobiSys (ACM, New York, 2010), pp. 49–62Google Scholar