Weighted utility aware computational overhead minimization of wireless power mobile edge cloud

Fifth-generation (5G) wireless networks are projected to support a large number of low-power devices, which are an essential component of Internet of Things (IoT) technologies. The existing network design is expected to face a number of challenges in serving such massive additional devices. Furthermore, these devices are bound by limited power processing and storage capacity, despite the fact that they are supposed to analyze massive volumes of data. In the last decade, the concepts of cloud and edge computing have received significant attention in order to increase network performance. Furthermore, wireless power transfer (WPT) is integrated with the cloud for energy transmission to low-power devices. This work presents a mathematical model for scheduling tasks that are being executed at low-power devices and concurrently on the cloud edge. The proposed mathematical model takes into account practical constraints and is intended to distribute resources among devices optimally while minimizing network overhead. To deal with the conflicting constraints, the model is further transformed into an unconstrained one. To solve the proposed model, evolutionary methods are being explored. Finally, a Monte Carlo simulation is used to validate the model. The simulation results show that partial offloading outperforms the edge-only computation scheme, with the partial offloading scheme demonstrating a 20% improvement in network overhead.