An Evaluation Study On Deployment Faults Of Deep Learning Based 5gmobile Applications

Abstract

With the development of Internet of Things (IoT), the quantity of mobile terminal devices is increasing rapidly. We aspire to reduce the
energy consumption of all the UE;s by optimizing the UAV’s trajectories, utilize associations and resource allocations. To tackle the multiUAV’s trajectories problem, a convex optimization-based CAT has been proposed. A DRL based AMECT including a matching algorithm has
also been proposed. Simulation results explain that AMECT performance. Our analysis on the process of deploying Deep Learning models to
mobile devices. This paper explain about the high transmission delay as well as limited bandwidth that can be considered the flying
Advanced Mobile Edge Computing Taxonomy architecture, by taking advantage of the UAV’s helps to serve as the moving platform. Any
drawbacks related to this process are within our scope. The system can still sustain very good presentation with the rapid expansion of the
number of utilizers or the amount of data