MADRL-Based Resource Allocation for UAV-Assisted Mobile Edge Computing

Toward Low-Delay and Energy-Efficient UAV-Assisted MEC Systems Through Intelligent Resource Allocation

A Prioritized Adaptive Weighting based on Deep Deterministic Policy Gradient (PAW-DDPG) as an enhanced Deep Deterministic Policy Gradient (DDPG) algorithm to minimize both processing delay and energy consumption by jointly optimizing user scheduling, partial-task offloading, and UAV trajectory is proposed.

Energy-Efficient Task Offloading and Load Balancing for Multi-UAV-Assisted Vehicular Networks

The rapid growth of Internet of Vehicles (IoV) applications has imposed strict requirements on low-latency and energy-efficient computing services. This letter investigates a multi-Uncrewed Aerial Vehicle (UAV)-assisted IoV system, where multiple Mobile Edge Computing (MEC)-enabled UAVs (MUs) collaboratively provide computing services for vehicular terminals (VTs). To improve service capability, we propose an energy-efficient task offloading and load balancing scheme that jointly considers vehicle mobility, task offloading and migration, and computing resource allocation to formulate an optimization problem. To solve this problem, a collective learning (CL)-enabled multi-agent reinforcement learning (CL-MARL) algorithm is proposed, where each agent learns optimal policies through centralized training and collective cooperative learning. Simulation results demonstrate that the proposed scheme outperforms benchmark strategies in terms of energy efficiency, task completion rate, and load balancing.

Joint Task Offloading and Resource Allocation for UAV Swarm Networks

This paper investigates the task offloading and resource allocation problem in unmanned aerial vehicle (UAV) swarm networks, with the objective of minimizing a weighted sum of task completion latency and energy consumption. Considering the autonomous decision‐making characteristics of individual UAVs in the swarm, each UAV is modeled as an intelligent agent and classified into heterogeneous types according to its computational capability. Based on this modeling framework, a mixed‐integer nonlinear programming (MINLP) problem is formulated to jointly optimize task offloading decisions and UAV transmission power. Owing to the high computational complexity of the original problem, it is decomposed into a transmission power allocation subproblem and a task offloading subproblem, where the optimal transmission power allocation strategy is obtained via a bisection‐based method. Furthermore, to enable efficient and rational task offloading within the UAV swarm, a matching game‐based task offloading algorithm is proposed, and its stability and convergence are theoretically proven. Finally, extensive simulation results and comparisons with multiple baseline schemes demonstrate the effectiveness and superiority of the proposed approach in terms of system latency and energy efficiency.

Joint Trajectory and Power Optimization for UAV-Relay: A Constraint Handling Approach with the Bat Algorithm

— Unmanned Aerial Vehicles (UAVs) have emerged as flexible relay platforms capable of enhancing wireless connectivity in beyond-5G and 6G networks. This paper investigates the joint optimization of UAV trajectory and power allocation to maximize end-to-end throughput under practical mobility and power constraints. The problem is highly non-convex due to the strong coupling between trajectory variables and transmission power. To address this challenge, we develop a penalty-based metaheuristic framework that incorporates a constraint-handling mechanism into the Bat Algorithm (BAT). Simulation results show that the proposed BAT-based approach achieves significant throughput improvement, efficient power allocation, and fast convergence compared with baseline convex optimization and heuristic schemes. These findings highlight the potential of BAT for reliable and energy-efficient UAV-assisted communication in future wireless networks.

Centralized Scheduling and Distributed Trajectory Optimization for Cooperative Mapping with Multiple PX4-Based VTOL UAVs

Multi-Algorithm-Based UAV Routing Optimization for Low-Altitude Logistics Scenarios

Unmanned Aerial Vehicles (UAVs) are now indispensable in low altitude urban logistics for their efficiency and versatility. In order to boost their practical performance in such a mission, in this paper, we study three typical UAV dispatching problems: (1) single UAV routing with battery constraints, (2) multi UAV task allocation and routing balance and (3) multi UAV minimization of UAVs with hard time window constrains. The mathematical models of each case are constructed, and the optimization algorithm such as greedy algorithm, cluster algorithm, genetic algorithm and simulated annealing algorithm are designed for each case. The simulation shows that greedy algorithm has better optimization in resource utilization and the convergence of the simulated annealing algorithm is better under the complex constraints. This results provide an algorithmic insight for the improved UAV scheduling problem in MUCLL environment.