Reinforcement Learning with UAV Assistance for Optimized Computation Offloading in Mobile Edge Computing

Abstract

With the rise of computing-intensive applications like online gaming and telemedicine on user equipment (UE) and the evolution of 5G technology, there is a surge in demand for greater computing resources and power. Yet, UEs have limited resources and batteries. Mobile Cloud Computing (MCC) has emerged as a method to enhance UEs computing capabilities and conserve energy by transferring tasks to the cloud. Mobile Edge Computing (MEC) further aids by reducing delays, although it faces issues like limited resources and unpredictable network conditions. Unmanned Aerial Vehicles (UAVs) offer a remedy by serving as mobile stations for MEC, but optimal offloading decisions in UAV-assisted MEC remain intricate. Addressing this, I propose using Reinforcement Learning (RL), specifically Q-Learning, Deep Q Network (DQN), and Deep Deterministic Policy Gradient (DDPG), to enhance decision-making for offloading. Our focus is on energy efficiency and reduced service delay, and our simulations prove our method's efficacy in UAV-assisted MEC environments.

Keywords

• mobile edge computing
• unmanned aerial vehicles
• reinforcement learning
• deep q network
• and deep deterministic policy gradient