JOTE: Joint Offloading of Task and Energy in Fog-Enabled IoT Networks

Abstract

Fog computing is considered to be a promising solution to enable latency-critical applications in Internet of Things (IoT). In this paper, we consider a fog-enabled IoT network where the task node can offload both the tasks and the energy to the helper nodes by applying the simultaneous wireless information and power transfer (SWIPT) technology. The task node first offloads energy to the helper nodes and then offloads the tasks to the helper nodes according to a time division multiple access (TDMA) protocol and an optimized ordering. In order to jointly minimize the task execution delay and the energy consumption, we formulate a combinatorial optimization problem. A low-complexity algorithm is then proposed to solve it based on the decomposed sub-problems. Additionally, we characterize the sufficient condition under which the joint task and energy offloading becomes beneficial. We also derive the offloading probability when taking into account the random fading channels. We further show that it is always desirable to offload both the task and the energy from the task node when the number of helper nodes goes to infinity. Numerical results are provided to validate our proposed algorithm and theoretical results.