Energy Efficiency Based Path Planning and Computation Offloading Strategy in UAV-Assisted Mobile Edge Computing System

In mobile edge computing system, path planning and computation offloading strategy of UAV have an important impact on system energy efficiency. This article focuses on the energy consumption optimization problem of sensor devices and studies the joint optimization method in the scenario of unmanned aerial vehicle assisted mobile edge computing system. Firstly, establish a comprehensive energy consumption model for unmanned aerial vehicle flight energy consumption, communication overhead, and computation offloading, and construct the problem of maximizing energy efficiency. Considering the dynamic nature of the system and the long-term randomness of optimization problems, a deep reinforcement learning based online decision-making algorithm is proposed to achieve intelligent collaborative optimization of drone path planning and computation offloading through network model training and deployment. The simulation results show that the proposed algorithm can effectively reduce the total energy consumption of sensors in the system, improve energy efficiency performance, and outperform traditional optimization methods. This study provides a feasible solution for resource optimization of unmanned aerial vehicle assisted MEC systems.