面向无人机集群任务分配的DPSO-GA混合优化算法OA
A hybrid DPSO-GA optimization algorithm for task allocation in UAV swarms
针对无人机集群任务分配优化问题,提出一种改进的DPSO-GA混合优化算法,构建时序约束下的无人机集群任务分配复杂映射关系,采用自适应余弦调整惯性权重与学习因子,引入交叉和变异操作,提升算法全局搜索能力与极值收敛速度、精度.经与DPSO、GA算法对比仿真,数据表明该算法平均适应度值较DPSO与GA算法分别下降50.0%、10.7%,方差较DPSO与GA算法分别降低95.7%、79.9%,置信区间宽度仅为DPSO的20.7%、GA的44.8%,证明该算法在收敛性、稳定性、可靠性方面显著优于对比算法,对求解无人机集群多目标任务分配问题具有一定参考价值.
To address the optimization problem of task allocation for drone swarms,an improved hybrid DPSO-GA optimiza-tion algorithm is proposed.This approach constructs a complex mapping relationship for drone swarm task allocation under temporal constraints.It employs adaptive cosine adjustment for inertia weights and learning rates,while incorporating cross-over and mutation operations to enhance the algorithm's global search capability,convergence speed,and accuracy toward extremes.Simulation comparisons with DPSO and GA algorithms reveal that the proposed algorithm achieves an average fit-ness value reduction of 50.0%and 10.7%compared to DPSO and GA respectively,with variance reductions of 95.7%and 79.9%compared to DPSO and GA respectively.The confidence interval widths were only 20.7%and 44.8%of those for DPSO and GA,demonstrating the algorithm's significant superiority in convergence,stability,and reliability over the com-parison algorithms.This makes it a valuable reference for solving multi-objective task allocation problems in UAV swarms.
沈延安;孙昊;王耀
陆军兵种大学,安徽 合肥 230031陆军兵种大学,安徽 合肥 230031陆军兵种大学,安徽 合肥 230031
信息技术与安全科学
无人机集群任务分配时序约束离散粒子群遗传算法
UAV swarmstask allocationtemporal constraintsdiscrete particle swarmgenetic algorithm
《指挥控制与仿真》 2026 (2)
30-37,8
评论