The rapid evolution of Fifth-Generation(5G)networks and the strategic development of Sixth-Generation(6G)technologies have significantly advanced the implementation of air-ground integrated networks with seamless cove...The rapid evolution of Fifth-Generation(5G)networks and the strategic development of Sixth-Generation(6G)technologies have significantly advanced the implementation of air-ground integrated networks with seamless coverage.Unmanned Aerial Vehicles(UAVs),serving as high-mobility aerial platforms,are extensively utilized to enhance coverage in long-distance emergency communication scenarios.The resource-constrained communication environments in emergencies by classifying UAVs into swarm UAVs and relay UAVs as aerial communication nodes is inversitgated.A horizontal deployment strategy for swarm UAVs is formulated through K-means clustering algorithm optimization,while a vertical deployment scheme is established using convex optimization methods.The minimum-path trajectory planning for relay UAVs is optimized via the Particle Swarm Optimization(PSO)algorithm,enhancing communication reliability between UAV swarms and terrestrial base stations.A three-dimensional heterogeneous network architecture is realized by modeling spatial multi-hop relay links.Experimental results demonstrate that the proposed joint UAV relay optimization framework outperforms conventional algorithms in both coverage performance and relay capability during video stream transmission,achieving significant improvements in coverage enhancement and relay efficiency.This work provides technical foundations for constructing high-reliability air-ground cooperative systems in emergency communications.展开更多
空天地融合车载网场景下,无人机设备由于电池容量和能源有限,无法为任务卸载提供长期有效支持;低轨卫星受资源成本以及通信延迟、时延抖动的影响难以为大规模车联网任务提供稳定的高带宽通信服务。针对空天地融合车载网络场景下无人机...空天地融合车载网场景下,无人机设备由于电池容量和能源有限,无法为任务卸载提供长期有效支持;低轨卫星受资源成本以及通信延迟、时延抖动的影响难以为大规模车联网任务提供稳定的高带宽通信服务。针对空天地融合车载网络场景下无人机和低轨卫星的资源优化问题,提出了一种基于多任务深度强化辅助学习(Multi-Task Deep Reinforcement and Auxiliary Learning,MTDRAL)的任务卸载以及功率调整、缓存决策的方案。首先构建了任务切分与传输模型、时延模型、能耗模型、服务器计算与缓存模型和问题模型;然后,基于对任务处理时延、服务器能耗以及缓存命中率的综合考虑,给出了基于MTDRAL的任务卸载及资源调度方案;最后将所提方案与随机卸载策略方案、成功率贪婪决策方案、基于柔性动作-评价算法的多网络深度强化学习的卸载方案、基于深度确定性策略梯度算法的多网络深度强化学习的卸载方案进行了对比实验。实验结果表明:所提方案在服务器数量为14、车载终端数量为10时,综合得分相较于4种对比方案,分别领先约134.41%,31.32%,38.93%,29.49%;所提方案具有较好的性能,能更好地满足空天地融合车载网场景下的任务卸载需求。展开更多
文摘The rapid evolution of Fifth-Generation(5G)networks and the strategic development of Sixth-Generation(6G)technologies have significantly advanced the implementation of air-ground integrated networks with seamless coverage.Unmanned Aerial Vehicles(UAVs),serving as high-mobility aerial platforms,are extensively utilized to enhance coverage in long-distance emergency communication scenarios.The resource-constrained communication environments in emergencies by classifying UAVs into swarm UAVs and relay UAVs as aerial communication nodes is inversitgated.A horizontal deployment strategy for swarm UAVs is formulated through K-means clustering algorithm optimization,while a vertical deployment scheme is established using convex optimization methods.The minimum-path trajectory planning for relay UAVs is optimized via the Particle Swarm Optimization(PSO)algorithm,enhancing communication reliability between UAV swarms and terrestrial base stations.A three-dimensional heterogeneous network architecture is realized by modeling spatial multi-hop relay links.Experimental results demonstrate that the proposed joint UAV relay optimization framework outperforms conventional algorithms in both coverage performance and relay capability during video stream transmission,achieving significant improvements in coverage enhancement and relay efficiency.This work provides technical foundations for constructing high-reliability air-ground cooperative systems in emergency communications.
文摘空天地融合车载网场景下,无人机设备由于电池容量和能源有限,无法为任务卸载提供长期有效支持;低轨卫星受资源成本以及通信延迟、时延抖动的影响难以为大规模车联网任务提供稳定的高带宽通信服务。针对空天地融合车载网络场景下无人机和低轨卫星的资源优化问题,提出了一种基于多任务深度强化辅助学习(Multi-Task Deep Reinforcement and Auxiliary Learning,MTDRAL)的任务卸载以及功率调整、缓存决策的方案。首先构建了任务切分与传输模型、时延模型、能耗模型、服务器计算与缓存模型和问题模型;然后,基于对任务处理时延、服务器能耗以及缓存命中率的综合考虑,给出了基于MTDRAL的任务卸载及资源调度方案;最后将所提方案与随机卸载策略方案、成功率贪婪决策方案、基于柔性动作-评价算法的多网络深度强化学习的卸载方案、基于深度确定性策略梯度算法的多网络深度强化学习的卸载方案进行了对比实验。实验结果表明:所提方案在服务器数量为14、车载终端数量为10时,综合得分相较于4种对比方案,分别领先约134.41%,31.32%,38.93%,29.49%;所提方案具有较好的性能,能更好地满足空天地融合车载网场景下的任务卸载需求。
