|Berg, Florian; Dürr, Frank; Rothermel, Kurt: Increasing the Efficiency of Code Offloading in n-tier Environments with Code Bubbling.
In: Proceedings of the 13th Annual International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services.
Universität Stuttgart, Fakultät Informatik, Elektrotechnik und Informationstechnik.
-, 28. November 2016.
ISBN: 978-1-4503-4750-1/16/11; DOI: dx.doi.org/10.1145/2994374.2994375.
Artikel in Tagungsband (Konferenz-Beitrag).
|C.2.4 (Distributed Systems)
|Mobile Cloud Computing; Multi-tier Code Offloading; Cyber Foraging; Code Bubbling; n-tier environment
Code offloading strives for increasing the energy efficiency and execution speed of mobile applications on resource-constrained mobile devices. First approaches considered only a code offloading between two (or three) tiers, executing code either locally on the mobile device or remotely on a powerful server in the vicinity or in a distant cloud. However, new execution environments comprise multiple tiers, containing highly distributed heterogeneous resources. We present in this paper our Code Bubbling Offload System (CoBOS). CoBOS targets n-tier environments containing highly distributed heterogeneous resources with different performance characteristics and cost implications. In such n-tier environments, it is very costly for a resource-constrained mobile device to gather a global view on available resources. As a result, we propose the novel concept of code bubbling. Code bubbling moves code dynamically and adaptively towards more powerful and more distant tiers, enabling an efficient and scalable code offloading in n-tier environments. Each tier makes autonomous decisions to execute code in the tier or forward it further to the next tier. To support such a recursive escalation of code along autonomous tiers, CoBOS offloads self-contained offload requests that possess all of the required information for the processing. Our real-world evaluation shows that CoBOS decreases the energy consumption by 77% and the execution time by 83% for code offloading in n-tier environments.
|Universität Stuttgart, Institut für Parallele und Verteilte Systeme, Verteilte Systeme
|21. Oktober 2016