Deep RL-based Ellipsoidal Path Planning for MEC enabled UAVs to Minimize Data Transmission Latency and Energy Consumption of Mobile Devices

Abstract

Due to the flexible deployment and movement capability, unmanned aerial vehicles (UAVs) are being utilized as flying mobile edge computing (MEC) platforms, offering real-time computational resources and low-latency data processing for a wide range of applications. The aim of this article is to explore a multi-UAV-assisted MEC system where multiple UAVs move using ellipsoidal trajectory to provide MEC services to resource-constrained mobile devices in temporary hotspot areas such as festival areas that have delay-sensitive applications with varying task offloading requests. Depending on the position, size, shape, and orientation of the ellipsoidal trajectories, the coverage area, energy consumption of mobile devices, and task transmission latency changes. Moreover, the varying user densities and task offloading request rates make the problem more challenging. Thus, we formulate an optimization problem that finds the center position, major radius, minor radius, and rotation angle of the ellipsoidal trajectory of UAV-assisted MEC servers with the objective of minimizing transmission latency and energy consumption of mobile devices while taking into account the required data transmission rate, task transmission time, energy consumption and several system-related constraints. Then, we have transformed this optimization problem into a Markov decision process and propose a deep Q-learning-based ellipsoidal trajectory optimization (DETO) algorithm to resolve it. The results from our simulations demonstrate that our approach outperforms other baselines, particularly in terms of reducing latency and the energy required for mobile devices to transmit data.