Jul 2026· Digital Signal and Computer Communications· Vol 14294, pp. 142940P - 142940P-7· 0 citations· 6 references
Engineering
TL;DR
Simulation results demonstrate that, compared with P-DQN, SAC, and PADDPG, the proposed framework achieves superior joint performance, thereby verifying its effectiveness for multi-UAV ISAC joint optimization.
Abstract
This paper investigates the task assignment and joint resource optimization problem for integrated sensing and communication (ISAC) in multi-UAV systems. To support the cooperative execution of detection, tracking, and communication tasks, a unified optimization framework is formulated by jointly considering task assignment, power allocation, and bandwidth allocation. Specifically, the UAV set, task set, and task-specific performance models are first established, and the system state is characterized by task priority, remaining power, remaining bandwidth, and task completion status. Then, task assignment constraints, UAV power constraints, bandwidth constraints, and task-type constraints are incorporated into the optimization problem. By introducing task-priority weights and a task-balancing factor, the objective is formulated as the maximization of the overall joint performance of the system. Since the considered problem involves discrete task assignment variables, continuous resource allocation variables, and nonconvex coupled constraints, it is difficult to solve efficiently using conventional optimization methods. To address this issue, the problem is modeled as a Markov decision process (MDP), and a proximal policy optimization (PPO)-based solution framework is developed to jointly determine UAV selection, power allocation, and bandwidth allocation actions. Simulation results demonstrate that, compared with P-DQN, SAC, and PADDPG, the proposed framework achieves superior joint performance, thereby verifying its effectiveness for multi-UAV ISAC joint optimization.
This article investigates the dynamic multiobjective co-optimization problem in unmanned aerial vehicle (UAV)-assisted remote sensing systems, aiming to jointly optimize UAV placement, task scheduling strategies, and computing/communication resource allocation to minimize the system’s average processing latency and the total energy consumption of UAVs. Addressing the shortcomings of existing research, which often overlooks the computational capabilities of UAVs, optimizes only a single aspect, and fails to account for environmental dynamics, this work formulates the problem as a dynamic multiobjective optimization problem. A hybrid optimization framework named DSG, integrating swarm intelligence and evolutionary algorithms, is proposed. The framework first derives a closed-form optimal resource allocation solution for given deployment and scheduling strategies through theoretical analysis. It then employs an improved dynamic multiobjective evolutionary algorithm (DMOEA) to co-optimize UAV positions (continuous variables) and task scheduling (discrete variables). Experimental results demonstrate that DSG achieves significantly better normalized hypervolume performance than comparative algorithms across various system scales [number of UAVs, access points (APs), and sensors] while exhibiting good stability and scalability. This provides an effective solution for the efficient co-optimization of UAV-assisted edge computing in dynamic environments.
Bo Wang, Xiaoyun Qin, Zhifeng Zhang et al.· IEEE Internet of Things Jour...· 0 citations
A dual-fallback mechanism is constructed by a pruning-redundancy coalition formation scheme and a task- segmentation scheme, thereby enhancing both system operational efficiency and task-completion certainty of the proposed DPI algorithm.
This paper proposes a collaborative task allocation model for heterogeneous multi-UAV systems in missions with chain-structured task priorities and strict time constraints. The model considers key constraints, including UAV flight speed, task capability differences, execution limits, and ordered task dependencies, enabling accurate representation of coordinated chain task execution. Traditional approaches struggle to ensure both real time performance and feasibility when the number of tasks and UAVs grows. To address this challenge, we develop an Extended Consensus-Based Bundle Algorithm (E-CBBA). The algorithm extends the traditional CBBA framework by introducing a maximum gain task screening strategy, a feasible position set for path insertion, and a global task execution time matrix for distributed consensus and conflict resolution. These mechanisms ensure that each UAV evaluates and inserts tasks only under feasible priority, timing, and kinematic conditions. We prove the convergence and approximate optimality of E-CBBA. Extensive simulations show that E-CBBA achieves higher objective values and task completion rates than traditional CBBA and GA-based methods, while maintaining fast convergence, scalability to multiple sequential task types, robustness under moderate communication degradation, and feasibility in ROS 2 and Gazebo simulations. Note to Practitioners—Multiple unmanned aerial vehicles (UAVs) are increasingly deployed in real combat and emergency response missions, where tasks are often subject to strict time constraints and precedence relationships. As the number of tasks and UAVs grows, existing task allocation methods tend to suffer from excessive decision latency and frequent task conflicts, which severely degrade coordination efficiency. To address these challenges, we propose an extended consensus-based bundle algorithm (E-CBBA) that enables UAVs to rapidly identify feasible tasks and achieve coordinated task allocations while explicitly respecting task ordering and temporal constraints. The proposed algorithm extends the conventional CBBA framework by incorporating task dependency modeling and time feasibility checking, allowing scalable and conflict-free coordination in complex mission scenarios. Simulations demonstrate that the method significantly improves task completion rates and decision speed, and remains effective as the number of tasks and UAVs increases. Future work will incorporate online learning to enhance robustness. The algorithm can also be extended to multi-robot coordination scenarios such as emergency rescue, logistics delivery, and inspection missions.
Kang Wang, Dongzhao Wang, Meng-Zhen Li et al.· IEEE Transactions on Automat...· 0 citations
In temporary emergency communication coverage scenarios where terrestrial communication infrastructure is damaged or lacks sufficient capacity, UAVs equipped with base stations have emerged as an effective solution due to their flexible deployment and rapid response capability. However, in multi-UAV networks, the three-dimensional deployment of UAVs significantly affects air-to-ground link quality, while power allocation further determines the level of system interference and throughput performance. To address this issue, this paper considers a multi-UAV communication system and jointly takes into account user link reliability and service requirement satisfaction, thereby establishing a joint optimization model for QoS-constrained coverage and network throughput. To address the non-convex joint optimization problem, a problem-tailored dual-population cooperative NSGA-II framework, termed IDPC-NSGA-II, is developed. By coupling dual-population evolution, adaptive mutation, uncovered-user-guided local search, and interference-aware repair with the characteristics of multi-UAV emergency communications, the proposed method improves the trade-off between QoS-constrained coverage and network throughput. Simulation results in a representative emergency communication scenario show that the proposed method achieves a favorable trade-off between QoS-constrained coverage and throughput, and outperforms the compared algorithms under the considered network setting.
Guifen Chen, Ruiyang Liu· Digital Signal and Computer...· 0 citations
A hierarchical joint optimization algorithm is developed within a multi-agent deep reinforcement learning (MADRL) framework to coordinate UAVs and MTs in a distributed manner and outperforms other benchmarks under varying network scales and capabilities by jointly optimizing UAV operations and resource utilization.
Tiankui Zhang, Wenlong Xu, Tianyi Shi et al.· IEEE Internet of Things Jour...· 0 citations
Multi-UAV mobile edge computing can provide flexible computing services for ground users, but it introduces coupled decisions in user association, channel allocation, cooperative offloading, and power control. This paper studies collaborative task offloading in a multi-UAV-assisted MEC system. A multi-stage service process is modeled, including user-to-UAV uploading, local computation, UAV-to-UAV cooperative transmission, cooperative computation, and result return. A comprehensive performance objective is formulated by jointly considering task success rate, delay cost, and energy consumption. To solve the resulting mixed discrete-continuous sequential decision problem, we propose GNN-MAHPPO, a multi-agent hybrid-action PPO algorithm enhanced by dual-layer heterogeneous graph attention. The proposed method jointly optimizes user association, channel allocation, cooperative offloading ratios, and transmit powers. Simulation results show that the proposed method achieves a higher task success rate and lower completion delay and energy consumption than the representative baselines, demonstrating its effectiveness in coordinating access, cooperation, and resource allocation.
Xin-Miao Zhu, Yupeng Wang· 2026 8th International Confe...· 0 citations