eduzhai > Applied Sciences > Engineering >

An Online Algorithm for Computation Offloading in Non-Stationary Environments

  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: We consider the latency minimization problem in a task-offloading scenario,where multiple servers are available to the user equipment for outsourcingcomputational tasks. To account for the temporally dynamic nature of thewireless links and the availability of the computing resources, we model theserver selection as a multi-armed bandit (MAB) problem. In the considered MABframework, rewards are characterized in terms of the end-to-end latency. Wepropose a novel online learning algorithm based on the principle of optimism inthe face of uncertainty, which outperforms the state-of-the-art algorithms byup to ~1s. Our results highlight the significance of heavily discounting thepast rewards in dynamic environments.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...