Computation Offloading Decision Bounds in SWIPT-based Fog Networks

Computation sharing is one of the most promising services in fog computing allowing the Fog Nodes (FNs) to share among themselves data and tasks to be computed. In case of battery powered-FNs, energy consumption becomes an issue. Simultaneous Wireless Information and Power Transfer (SWIPT) is a recently introduced technology enabling data and power transfer through microwave links among different nodes. In this work, we have considered the presence of a battery powered FN able to simultaneously share data and harvest energy from a Fog Access Point (F-AP), supposed to be plugged to the electrical network. The aim of this work is to define two suitable bounds able to drive the offloading decision to be taken by the battery powered FN, based on the estimated packet generation time, with the aim of having a stable energy system. We have further studied the impact of bandwidth and packet size on the two bounds. Simulation results demonstrate the impact of SWIPT-based offloading decision algorithm on network in terms of latency and network lifetime.