Swarm UAV networking with collaborative beamforming and automated ESN learning in the presence of unknown blockages
Swarm UAV networking with collaborative beamforming and automated ESN learning in the presence of unknown blockages
复制标题
在存在未知阻塞的情况下，具有协作波束成形和自动 ESN 学习功能的无人机集群网络
DOI：
10.1016/j.comnet.2023.109804
复制
发表时间：
2023
影响因子：
5.6
通讯作者：
Guan, Zhangyu
中科院分区：
文献类型：
--
作者：
Krishna Moorthy, Sabarish;Mastronarde, Nicholas;Pudlewski, Scott;Bentley, Elizabeth Serena;Guan, Zhangyu
本文旨在设计具有分布式波束形成能力的高数据速率群无人机网络。主要挑战是群UAV网络中的波束形成增益受到UAV的飞行高度、它们的运动和由此产生的间歇性链路阻塞以及单个UAV处的信道状态信息（CSI）的可用性的高度影响。为了应对这一挑战，我们提出了FlyBeam，一个基于学习的框架，用于群无人机网络中的联合飞行和波束形成控制。首先，我们提出了一个数学公式的控制问题，其目标是通过联合控制无人机的飞行和分布式波束形成来最大化群无人机网络的吞吐量。然后，设计了一种基于回声状态网络（ESN）学习和在线强化学习相结合的分布式求解算法。前者是采用在线测量的基础上，通过共同考虑未知的阻塞动态和其他因素，影响波束形成增益的单个无人机近似的效用函数。后者用于指导FlyBeam的开发和探索。我们进一步设计了一个自动化训练ESN模型的方案AutoESN，AutoESN可以使用损失函数和步长的组合来自动更新可配置的ESN参数。FlyBeam的有效性是通过在UBSim上进行广泛的仿真活动来评估的，UBSim是一个基于Python的通用宽带仿真器，用于集成空中和地面无线网络。FlyBeam的性能与两个基准方案进行了比较，一个是基于传统优化技术设计的，另一个是基于长短期记忆（LSTM）的效用函数近似学习。在性能评估中，我们考虑了迫零（ZF）和最大比传输（MRT）的波束形成顺序和同时信道状态估计。结果表明，显着的（高达450%）波束形成增益可以通过FlyBeam实现。我们还研究了阻塞和无人机飞行高度对波束形成增益的影响。研究发现，在阻塞密集的无人机集群网络中，FlyBeam可以获得更高（而不是更低）的波束形成增益。
This paper aims at designing high-data-rate swarm UAV networks with distributed beamforming capabilities. The primary challenge is that the beamforming gain in swarm UAV networks is highly affected by the UAVs’ flight altitude, their movements and the resulting intermittent link blockages, as well as the availability of channel state information (CSI) at individual UAVs. To address this challenge, we proposeFlyBeam, a learning-based framework for joint flight and beamforming control in swarm UAV networks. We first present a mathematical formulation of the control problem with the objective of maximizing the throughput of swarm UAV networks by jointly controlling the flight and distributed beamforming of UAVs. Then, a distributed solution algorithm is designed based on a combination of Echo State Network (ESN) learning and online reinforcement learning. The former is adopted to approximate the utility function for individual UAVs based on online measurements, by jointly considering the unknown blockage dynamics and other factors that affect the beamforming gain. The latter is used to guide the exploitation and exploration inFlyBeam. We further design a scheme referred to asAutoESNto automate the training of the ESN model.AutoESNcan update the configurable ESN parameters automatically using a combination of loss function and step size. The effectiveness ofFlyBeamis evaluated through an extensive simulation campaign on UBSim, a Python-based Universal Broadband Simulator for integrated aerial and ground wireless networking. The performance ofFlyBeamis compared with two benchmark schemes, one designed based on traditional optimization techniques and the other based on learning with utility function approximation through Long Short-Term Memory (LSTM). In the performance evaluation, we consider both Zero-Forcing (ZF) and Maximum Ratio Transfer (MRT) for beamforming with sequential and simultaneous channel state estimation. It is shown that significant (up to 450%) beamforming gain can be achieved byFlyBeam. We also investigate the effects of blockages and UAV flight altitude on the beamforming gain. It is found that, somewhat surprisingly, higher(rather than lower)beamforming gain can be achieved byFlyBeamwith denser blockages in swarm UAV networks.
影响因子：
10.4
作者：
Cui, Jingjing;Liu, Yuanwei;Nallanathan, Arumugam
通讯作者：
Nallanathan, Arumugam
影响因子：
10.4
作者：
Challita, Ursula;Saad, Walid;Bettstetter, Christian
通讯作者：
Bettstetter, Christian