Resource Optimization And Path Planning In Mobile Edge Computing Scenario

When the basic network facilities are damaged and cannot work normally,a “mobile edge computing system” composed of unmanned aerial vehicles(UAVs)and other carriers is required to provide stable and reliable services.However,the UAV consumes a substantial number of energy resources when it is utilized to provide edge computing services.Premised on resource optimization,this paper encompasses an analysis of energy harvesting technologies,energy consumption optimization of UAV and UAV path planning in mobile edge computing(MEC),thereby optimizing the energy consumption of UAV edge computing system and enhancing the quality of service of the system.In this study,the following contents are expounded:(1)Energy harvesting technologies in mobile edge computing.In the light of energy constraints in edge computing,the present author adopts the simultaneous wireless information and power transfer to harvest the energy in radio frequency signals,setting forth the optimization of system energy efficiency,UAV energy efficiency and the maximum feasible hops of UAV formation.In addition,the optimization problems proposed by the Dinkelbach algorithm and the generalized Benders decomposition method effectively improve the energy efficiency and endurance of the system.(2)UAV energy consumption optimization in mobile edge computing.In terms of energy constraints of UAVs,this paper is devoted to the modeling of UAV energy consumption during its flight and data unloading,and proposes the optimization of UAV weighted energy consumption during its task execution.Moreover,the successive convex optimization and alternating optimization algorithm are employed to solve the related problems,and the simulation validity test of the superiority of the algorithm in energy consumption optimization is provided as well.(3)UAV path planning based on reinforcement learning in mobile edge computing.In view of the limitations of the previous UAV path planning with safe obstacle avoidance as the top priority,this paper focuses on the data requirements of ground base stations,and takes into account the safe obstacle avoidance of UAV during their flights.A path planning algorithm based on Q-learning is designed by establishing Markov process and in virtue of the modeling of UAV energy consumption during its flight and data unloading.This algorithm has achieved a balance between safe obstacle avoidance and data unloading services for ground base stations,which can effectively improve the quality of service of the system.