多无人机辅助通信中用户匹配与频谱资源联合优化方法

针对多无人机作为空中基站为地面设备提供临时服务的动态频谱分配问题，主要考虑无人机与地面用户匹配、子信道分配和功率分配三个方面。为了保证用户通信的公平性，在考虑频谱复用和共信道干扰的情况下，以最大化地面用户最小传输速率为目标，提出了一种用户匹配与频谱资源联合优化算法来解决上述混合整数非线性优化问题，通过聚类算法优化无人机与地面用户的最佳匹配，通过块坐标下降法迭代优化子信道分配和功率分配。仿真实验分析表明，提出的求解方法可以有效提升用户的传输速率，保证用户通信公平性。     

基于强化学习的无人机电磁干扰感知与抗干扰传输方法

无人机对于无线信道的依赖性和无线传播环境的开放性,导致其通信易受到恶意的电磁干扰。针对其中恶意的信道跟随干扰,在感知干扰信道信息的基础上,将无人机的发射功率和信道选择策略建模为马尔科夫决策过程(Markov Decision Process, MDP),利用强化学习算法对该通信系统的抗干扰方法进行智能优化,提出了基于赢或快学习策略爬山算法(Win or Learn Fast Policy Hill-climbing, WoLF-PHC)的抗干扰算法。仿真结果证明,所提算法能够将用户干信比降低至0.1以下,将用户可达速率在初始值基础上提升14%,与Q学习算法和PHC算法相比具有更好的抗干扰传输性能。     

基于K-臂赌博机的多无人机空地网络动态资源分配方法

针对配置大规模MIMO的多无人机空地网络中的动态资源分配问题,从最大化系统吞吐量的角度出发,该文提出一种基于K-臂赌博机的强化学习算法联合优化多个无人机的用户选择与功率分配策略。首先根据地理位置对用户进行分簇,利用簇中心节点规划无人机飞行路径;其次在不考虑无人机之间端到端通信的情况下,将多无人机资源分配问题转化为相互独立的多个智能体强化学习问题;最后提出分幕式多智能体多状态K-臂赌博机算法来实现用户选择与功率分配的联合优化。通过将无人机每个时刻的位置索引定义为状态空间,从而使得无人机可动态适配自身位置及信道的动态变化。仿真结果表明,所提方案可根据环境状态变化自主智能调整资源分配策略,相比于已有方案能有效提升系统总吞吐量。     

基于多智能体强化学习的空地网络抗干扰传输方法研究

提出了一种基于多智能体强化学习的抗干扰传输算法,旨在抵御空地一体化网络中的功率干扰,使所有用户的可达速率之和最大化。将优化问题转化为部分可观察马尔可夫决策过程问题,采用了集中式训练和分布式执行框架。在集中式训练过程中,每个智能体与环境交互获得的经验存储在经验回放池中,用于训练演员-评论员网络。在分布式执行过程中,每架无人机使用经过训练的演员网络根据观测结果输出动作,并调整其飞行位置和传输功率以提供联合服务。采用基于剪切和计数的改进近端策略优化算法来更新演员-评论员网络参数,使其在复杂的多智能体环境中更加有效。仿真结果表明,所提算法相较于对比算法具有更快的收敛速度,且在相同干扰条件下,所提算法比对比算法获取的用户可达和速率提升约68.9%。     

无线传感器网络中支持并行传输的信道与功率联合优化博弈算法

针对无线传感器网络中干扰日益增大引起网络容量下降、能耗增加的问题,该文建立了信道分配与功率控制联合优化博弈模型。在该模型中链路将既能保持自身成功传输又不影响其它链路传输的信道作为可选信道,以实现链路的并行传输。继而基于该模型设计了一种支持并行传输的信道分配与功率控制联合优化博弈算法(JCPGC)。该算法利用最佳响应策略对模型求解,并通过超模博弈等理论证明了JCPGC能够收敛到纳什均衡。此外,该算法充分考虑信道分配和功率控制之间独立又相互影响的关系提高了网络容量。仿真实验结果表明,JCPGC具有大容量、低干扰和低能耗的特性。     

主动干扰辅助下的无人机隐蔽通信功率与位置联合优化

利用友好干扰节点发送人工噪声是无线隐蔽通信中一种常见实现方法,可以增加监听者做出判断的不确定性,从而实现隐蔽传输。为此,考虑在无人机隐蔽通信网络中,部署一个空中的友好干扰节点,发射人工噪声干扰地面监听者的检测。对无人机与地面用户之间实现无线隐蔽传输进行了研究,分析了其有效隐蔽性能,联合优化了2架无人机的发送功率和位置部署以最大化隐蔽传输速率,使用粒子群优化算法与功率位置交替迭代算法2种优化方法得到最优的无人机部署位置及功率分配方案。仿真结果表明,联合优化方案相比于固定位置只优化功率的基准方案可以显著地提高系统隐蔽传输性能,且交替迭代算法所得结果要优于粒子群优化算法。     

基于深度强化学习的多域联合干扰规避

无线通信系统的信道开放性使其极易受到外部恶意干扰、通信链路质量难以保证,针对以上问题,本文设计了一种基于深度强化学习的多域联合干扰规避决策方法。该方法联合频域、功率域、调制编码域三个域的抗干扰手段进行干扰规避,在考虑系统性能的同时实现可靠通信。首先,将联合智能干扰规避问题建模为一个马尔可夫决策过程（MDP, Markov Decision Process）,动作空间包含切换信道、功率控制、改变调制编码方式。然后,采用基于剪裁的近端策略优化算法（PPO-Clip, Proximal Policy Optimization-Clip）求解获得系统的最优联合干扰规避策略。PPO-Clip算法在多回合训练中以小数量样本迭代更新,避免了策略梯度算法中步长难以确定和更新差异过大的问题。最后,分别在扫频干扰、随机扫频干扰和智能阻塞干扰环境下验证了所提算法的有效性和可靠性。      

基于PSO的D2D蜂窝网络联合信道分配和功率控制

为解决蜂窝用户(Cellular Users, CU)和终端直通(Device to Device, D2D)用户之间的干扰管理问题,提高无线蜂窝网络吞吐量,提出了一种基于粒子群优化的联合信道分配和功率控制方案。提出了具有不同约束条件的2个联合信道分配和功率控制问题,并将离散信道和连续功率联合分配给CU和D2D对,允许任意数量的D2D对与一个CU共享同一信道。通过设计适应度值避免算法陷入局部最优或产生不可行的解决方案,并使算法收敛到全局最优。通过搭建仿真网络模型进行测试验证,并与随机粒子群优化算法进行对比分析。实验结果表明,所提方法可有效提高蜂窝网络中的D2D通信网络吞吐量,且与随机粒子群优化算法相比,所提方法在D2D吞吐量、蜂窝吞吐量以及整体网络吞吐量方面具有明显优势。     

无线传感器网络基于容量和传输能耗的功率与信道联合博弈算法

针对无线传感器网络(WSNs)日益增大的干扰导致网络容量下降的问题,同时考虑到网络能量有限性,该文综合网络容量和链路传输能耗,构建了高容量低传输能耗的功率控制与信道分配联合博弈模型,并通过理论分析证明该模型存在最优功率和最优信道。继而采用最佳响应策略,在该博弈模型基础上提出了一种功率控制与信道分配联合优化算法(PCOA),理论证明其能收敛到纳什均衡状态,且具有较小的信息复杂度。最后,仿真结果表明,PCOA算法能够达到降低网络干扰和链路能耗,增大网络容量的目的。     

恶意干扰下基于斯坦伯格博弈的无人机动态频谱分配

针对恶意干扰场景下无人机群动态频谱分配问题,构建了基于斯坦伯格博弈的动态频谱分配模型,干扰机为斯坦伯格博弈的领导者,无人机群为斯坦伯格博弈的跟随者,设计了不同博弈参与者的效益函数,并证明了该博弈存在稳定的斯坦伯格均衡解。在此基础上设计了一种分层动态频谱分配算法,针对领导者采用Q学习选择干扰信道的场景下,跟随者采用随机学习自动机来确定信道分配策略。仿真结果表明,所提算法能够得到无人机用户的最优信道分配策略,有效提升无人机用户的总吞吐量性能,实现效益最大化。     

Hierarchical game based spectrum access optimization for anti-jamming in UAV network

For the anti-jamming spectrum access optimization problem in unmanned aerial vehicle (UAV) communication networks,considering the complex and diverse malicious jamming from jammers,a Bayesian Stackelberg game was proposed to formulate the competitive relations between UAV users and jammers.Specifically,jammers acted as the leader,whereas users acted as followers of the proposed game.Based on their different utility functions,the jammer and users independently and selfishly selected their optimal strategies and obtained the optimal channels selection.Due to the NP-hard nature,it was challenging to obtain the Stackelberg Equilibrium of the proposed game.To this end,a hierarchical learning framework was formulated,and a hierarchical channel selection-learning algorithm was proposed.Simulations demonstrate that with the proposed hierarchical learning algorithm,UAV nodes can adjust their channel selection and obtain superior performance.     

一种基于服务质量的多UAV容量优化方法

随着近些年来通信领域各种技术的高速发展,UAV因为其体积小、灵活性强、可快速部署等优点,越来越受到通信领域相关学者的青睐。同时,由于UAV在各个领域的应用逐渐增多,UAV网络的容量优化问题变得越来越重要。针对未来大规模用户的通信需求,提出了一种基于服务质量的多UAV容量优化方法。首先将服务质量设置为权重参数,联合用户调度、轨迹和功率分配,利用连续凸优化技术和块坐标下降算法,提出多UAV通信系统中的的容量优化算法。仿真结果证明该算法的收敛性,同时表明在相同条件下基于用户质量的多UAV容量算法能够使系统达到更高的平均传输速率。     

面向隐蔽侦察任务的无人机中继通信频谱资源优化方法

战场环境下,无人机因其自身辐射被敌侦收而产生安全威胁,并容易对其他通信网络产生干扰。为提高无人机安全执行战场侦察任务时的侦察信息传输速率,提出面向隐蔽侦察任务的无人机中继通信频谱资源优化方法,通过功率控制避免被敌方反侦测,并利用无人机中继增大系统通信速率,通过频谱资源优化达到无有害干扰通信的目的。同时提出了基于块坐标下降法与连续凸近似法相结合的频谱资源联合优化算法,通过对带宽分配、发射功率和无人机轨迹等变量的联合优化获得次优解。仿真结果表明：与基准策略相比,联合优化算法具有更高的信息传输速率。     

基于MADDPG的无人机辅助通信功率分配算法

针对多无人机(unmanned aerial vehicle, UAV)作为空中基站辅助通信的吞吐量和公平性问题,提出了一种基于多智能体深度确定性策略梯度算法(multi-agent deep deterministic policy gradient algorithms, MADDPG)的功率分配算法,该算法通过联合优化UAV基站的功率分配和用户接入以提高系统吞吐量和公平性。本文首先构建了UAV基站为地面建立通信服务的三维场景,然后通过联合功率、用户关联和UAV位置约束,构建了吞吐量和公平性最大化的问题模型。考虑到该问题的复杂性,本文将所构建的优化问题建模为马尔科夫决策过程(Markov decision process, MDP),通过引入深度确定性策略梯度算法(deep deterministic policy gradient algorithm, DDPG)解决该问题。仿真结果表明,本文提出的基于MADDPG的UAV基站功率分配算法与其他算法相比,可以有效地提升系统的吞吐量和用户的公平性,提高通信的服务质量。     

Joint power allocation and beamforming with users selection for cognitive radio networks via discrete stochastic optimization

Cognitive radio is a promising technique to dynamic utilize the spectrum resource and improve spectrum efficiency. In this paper, we study the problem of mutual interference cancellation among secondary users (SUs) and interference control to primary users (PUs) in spectrum sharing underlay cognitive radio networks. Multiple antennas are used at the secondary base station to form multiple beams towards individual SUs, and a set of SUs are selected to adapt to the beams. For the interference control to PUs, we study power allocation among SUs to guarantee the interference to PUs below a tolerable level while maximizing SUs?? QoS. Based on these conditions, the problem of joint power allocation and beamforming with SUs selection is studied. Specifically, we emphasize on the condition of imperfect channel sensing due to hardware limitation, short sensing time and network connectivity issues, which means that only the noisy estimate of channel information for SUs can be obtained. We formulate the optimization problem to maximize the sum rate as a discrete stochastic optimization problem, then an efficient algorithm based on a discrete stochastic optimization method is proposed to solve the joint power allocation and beamforming with SUs selection problem. We verify that the proposed algorithm has fast convergence rate, low computation complexity and good tracking capability in time-varying radio environment. Finally, extensive simulation results are presented to demonstrate the performance of the proposed scheme.     

无蜂窝大规模MIMO中基于深度强化学习的无人机辅助通信与资源调度

无蜂窝大规模多入多出(MIMO)网络中分布式接入点(AP)同时服务多个用户,可以实现较大区域内虚拟MIMO的大容量传输;而无人机辅助通信能够为该目标区域热点或边缘用户提供覆盖增强.为了降低反馈链路负载,并有效提升无人机辅助通信的频谱利用率,该文研究了基于AP功率分配、无人机服务区选择和接入用户选择的联合调度;首先将AP...     

A utility-based capacity optimization framework for achieving cooperative diversity in the hierarchical converged heterogeneous wireless networks

A hierarchical convergence mechanism for the heterogeneous wireless communication system via the heterogeneous cooperative relay node is presented in this paper, in which the techniques of cooperative communication and wireless relay are utilized to improve performances of the individual user and the overall converged networks. In order to evaluate the benefits of the proposal, a utility-based capacity optimization framework for achieving the heterogeneous cooperative diversity gain is proposed. The heterogeneous cooperative capacity, relay selection and power allocation theoretical models are derived individually. The joint optimization model for relay selection and power allocation is presented as well. Owing to the computation complexity, the sub-optimal cooperative relay selection algorithm, the sub-optimal power allocation algorithm and the sub-optimal joint algorithm are determined to approach the maximum overall networks' spectrum efficiency. These proposed algorithms are designed in conformance to guarantee the equivalent transmission rates of the different wireless access networks. The simulation results demonstrate that the utility-based capacity model is available for the heterogeneous cooperative wireless communication system, and the proposed algorithms can improve performances by achieving the cooperative gain and taking full advantage of the cross-layer design. Copyright © 2008 John Wiley & Sons, Ltd.     

Intelligent deep learning-aided future beam and proactive handoff prediction model in Unmanned Aerial Vehicle-assisted anti-jamming Terahertz communication system

Wireless communications often suffer from legitimate transmissions regarding malicious jamming attacks launched through the smart jammer. The drone or unmanned aerial vehicle (UAV) communication networks derived with reconfigurable intelligent surfaces (RIS) increase the issues of beam selection and proactive handoff in terahertz (THz). Thus, a new heuristic strategy is designed for efficient and incorporated optimization of the beamforming vector and anti-jamming transmit power allocation in undefined environments. Here, the transmit power allocation and beamforming matrix of UAV are optimized with the developed hybrid heuristic algorithm of the Hybrid Crow Black Widow Search Optimization (HCBWSO) algorithm for maximizing the system achievable rate. Here, the HCBWSO algorithm is implemented to integrate with the Crow search algorithm (CSO) and Black Widow Optimization (BWO). The second contribution is to adopt RIS into THz–UAV communications, a new Enhanced Deep Temporal Convolutional Network (EDTCN) for predicting the future beam and proactive handoff of UAVs based on their prior analysis of the UAV locations, where the HCBWSO algorithm is utilized for recommending EDTCN. Here, the training of the EDTCN needs to be done with the collection of UAV information from the DEEPMIMO dataset for predicting the future beams and, also, tracking the location of the UAV. EDTCN helps in increasing the possibility of expanding the UAV coverage and also increases the consistency of the THz communication system. Thus, the prediction of the future beam increases the coverage area of the UAV and also maximizes the system rate in the THz communication system.