Sterz, Artur ; Baumgärtner, Lars ; Höchst, Jonas ; Lampe, Patrick ; Freisleben, Bernd (2019)
OPPLOAD: Offloading Computational Workflows in Opportunistic Networks.
44th IEEE Conference on Local Computer Networks (LCN 2019). Osnabrück, Germany (14.-17.10.)
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

Computation offloading is often used in mobile cloud computing, edge computing, and/or fog computing to cope with resource limitations of mobile devices in terms of computational power, storage, and energy. Computation offloading is particularly challenging in situations where network connectivity is periodic, intermittent, or error-prone. In this paper, we present OPPLOAD, a novel framework designed for offloading computational workflows in opportunistic networks that provide support for communication in such situations. The individual tasks forming a workflow can be assigned to particular remote execution platforms, called workers, either preselected ahead of time or decided just in time where a matching worker will automatically be assigned for the next task in the workflow. Workers announce their capabilities, i.e., tasks are only assigned to capable workers. Furthermore, tasks of a workflow can be executed on multiple workers that are automatically selected to balance the overall load. OPPLOAD also offers the ability to handle several types of error and exceptions appropriately. Our Python implementation of OPPLOAD, which uses the Serval Mesh to handle networking and routing, is publicly available as open source software. The results of our experimental evaluation demonstrate the feasibility of our approach.

Frage zum Eintrag

Redaktionelle Details anzeigen