Online optimal task offloading with one-bit feedback
This work addresses efficient resource allocation for users in fog-enabled networks, but it appears incremental as it applies a known UCB-type algorithm to a specific scenario.
The paper tackled the problem of stochastic task offloading in fog networks by proposing a multi-armed bandit framework to maximize long-term happiness based on one-bit feedback from helper nodes, with numerical simulations used to validate the strategy.
Task offloading is an emerging technology in fog-enabled networks. It allows users to transmit tasks to neighbor fog nodes so as to utilize the computing resources of the networks. In this paper, we investigate a stochastic task offloading model and propose a multi-armed bandit framework to formulate this model. We consider the fact that different helper nodes prefer different kinds of tasks. Further, we assume each helper node just feeds back one-bit information to the task node to indicate the level of happiness. The key challenge of this problem lies in the exploration-exploitation tradeoff. We thus implement a UCB-type algorithm to maximize the long-term happiness metric. Numerical simulations are given in the end of the paper to corroborate our strategy.