Task energy efficiency optimization-oriented unmanned aerial vehicle dynamic position deployment control method and device

By constructing a multi-model UAV mobile edge computing system and adopting distributed matching game theory and multi-objective reward function optimization strategies, the problems of user association conflict and energy efficiency in UAV systems under dynamic high-density service scenarios are solved, and system-level load balancing and efficient task processing are achieved.

CN122363246APending Publication Date: 2026-07-10PUTIAN UNIV
0 Cites 0 Cited by

Patent Information

Application Number
CN202610234914.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-02-27
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing UAV mobile edge computing systems face problems such as user association conflicts, uneven computing load, and insufficient system energy efficiency optimization in dynamic high-density service scenarios. Especially in complex scenarios where the location of ground equipment changes dynamically and task requirements are generated randomly, traditional methods are difficult to adapt to the dynamic fluctuations of the environment in real time, resulting in the inability to guarantee system energy efficiency and service quality.

Method used

A mobile edge computing system model for unmanned aerial vehicles (UAVs) is constructed, which includes continuous domain kinematics, air-to-ground communication transmission, latency calculation, and energy consumption model. A multi-agent deep deterministic policy gradient algorithm is used to generate deterministic action vectors. Task association is achieved through distributed matching game. Latency, energy consumption, and task completion are optimized through a multi-objective reward function. The policy network is trained and updated in combination with a centralized network model.

Benefits of technology

It achieves system-level load balancing, has real-time decision-making capabilities in highly dynamic environments, significantly improves the overall energy efficiency of the system, and can optimize the flight trajectory and task offloading of UAV swarms in complex application scenarios, thereby improving the utilization of computing resources and service quality.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a task energy efficiency optimization-oriented unmanned aerial vehicle dynamic position deployment control method and device, and relates to the technical field of unmanned aerial vehicle communication control. According to the method, an unmanned aerial vehicle mobile edge computing system model is constructed, a current environment state is collected in each discrete time step to generate a local observation vector, and a deterministic action vector is generated; then executing a distributed matching game with a ground mobile device to complete task association; then, position updating is executed, a multi-target reward function is calculated, centralized network model training is carried out, and the Critic evaluation network and the Actor strategy network are iteratively updated; and when the model training meets a preset requirement, the training is terminated, and an unmanned aerial vehicle dynamic position deployment control strategy with optimal task energy efficiency is obtained. According to the method, deep coupling optimization of the physical track and the unloading decision can be realized, the problems of user association conflict and uneven calculation load in a dynamic scene are effectively solved, and the comprehensive energy efficiency of the system is remarkably improved while the service quality is guaranteed.
Need to check novelty before this filing date? Find Prior Art