Directional Routing Algorithm for Deep Space Optical Network

With the development of science, economy and society, the needs for research and exploration of deep space have entered a rapid and stable development stage. Deep Space Optical Network(DSON) is expected to become an important foundation and inevitable development trend of future deepspace communication. In this paper, we design a deep space node model which is capable of combining the space division multiplexing with frequency division multiplexing. Furthermore, we propose the directional flooding routing algorithm(DFRA) for DSON based on our node model. This scheme selectively forwards the data packets in the routing, so that the energy consumption can be reduced effectively because only a portion of nodes will participate the flooding routing. Simulation results show that, compared with traditional flooding routing algorithm(TFRA), the DFRA can avoid the non-directional and blind transmission. Therefore, the energy consumption in message routing will be reduced and the lifespan of DSON can also be prolonged effectively. Although the complexity of routing implementation is slightly increased compared with TFRA, the energy of nodes can be saved and the transmission rate is obviously improved in DFRA. Thus the overall performance of DSON can be significantly improved.

A SURVEY OF DEEP SPACE COMMUNICATIONS

Deep space communications has played an important role in deep space exploration. Compared with common satellite and terrestrial communications, deep space communications faces more challenging environment. The paper investigated the unique features of deep space communica-tions in detail, discussed the key technologies and its development trends for deep space communica-tions.

A NEW ALGORITHM FOR MAIN CARRIER ACQUISITION IN DEEP SPACE COMMUNICATIONS

Compared with common near space satellite Telemetry,Telecommand,and Communication(TT&C),deep space TT&C presents a more challenging environment such as long distance,very low Signal to Noise Ratio(SNR).How to acquire main carrier exactly becomes a hot focus for deep space communications.Already there emerged some main carrier acquisition algorithms,but they all require high SNR and small modulation index.In this paper,we develop a new acquire algorithm.First we use the spectral energy center algorithm to shorten the original sequence,filter out some noise and make the spectral more symmetric.Then we adopt the spectral symmetry algorithm to make full use of the whole spectrum information,and utilize FFT to reduce computation complexity.Simulation results show that our algorithm can acquire main carrier successfully under large modulation index and get good performance with low Carrier to Noise Ratio(CNR).

Enhancing Collaborative and Geometric Multi-Kernel Learning Using Deep Neural Network

This research proposes a method called enhanced collaborative andgeometric multi-kernel learning (E-CGMKL) that can enhance the CGMKLalgorithm which deals with multi-class classification problems with non-lineardata distributions. CGMKL combines multiple kernel learning with softmaxfunction using the framework of multi empirical kernel learning (MEKL) inwhich empirical kernel mapping (EKM) provides explicit feature constructionin the high dimensional kernel space. CGMKL ensures the consistent outputof samples across kernel spaces and minimizes the within-class distance tohighlight geometric features of multiple classes. However, the kernels constructed by CGMKL do not have any explicit relationship among them andtry to construct high dimensional feature representations independently fromeach other. This could be disadvantageous for learning on datasets with complex hidden structures. To overcome this limitation, E-CGMKL constructskernel spaces from hidden layers of trained deep neural networks (DNN).Due to the nature of the DNN architecture, these kernel spaces not onlyprovide multiple feature representations but also inherit the compositionalhierarchy of the hidden layers, which might be beneficial for enhancing thepredictive performance of the CGMKL algorithm on complex data withnatural hierarchical structures, for example, image data. Furthermore, ourproposed scheme handles image data by constructing kernel spaces from aconvolutional neural network (CNN). Considering the effectiveness of CNNarchitecture on image data, these kernel spaces provide a major advantageover the CGMKL algorithm which does not exploit the CNN architecture forconstructing kernel spaces from image data. Additionally, outputs of hiddenlayers directly provide features for kernel spaces and unlike CGMKL, do notrequire an approximate MEKL framework. E-CGMKL combines the consistency and geometry preserving aspects of CGMKL with the compositionalhierarchy of kernel spaces extracted from DNN hidden layers to enhance the predictive performance of CGMKL significantly. The experimental results onvarious data sets demonstrate the superior performance of the E-CGMKLalgorithm compared to other competing methods including the benchmarkCGMKL.

Ultra reliability and massive connectivity provision in integrated internet of military things(IoMT)based on tactical datalink

One of the major challenges arising in internet of military things(IoMT)is accommodating massive connectivity while providing guaranteed quality of service(QoS)in terms of ultra-high reliability.In this regard,this paper presents a class of code-domain nonorthogonal multiple accesses(NOMAs)for uplink ultra reliable networking of massive IoMT based on tactical datalink such as Link-16 and joint tactical information distribution system(JTIDS).In the considered scenario,a satellite equipped with Nr antennas servers K devices including vehicles,drones,ships,sensors,handset radios,etc.Nonorthogonal coded modulation,a special form of multiple input multiple output(MIMO)-NOMA is proposed.The discussion starts with evaluating the output signal to interference-plus-noise(SINR)of receiver filter,leading to the unveiling of a closed-form expression for overloading systems as the number of users is significantly larger than the number of devices admitted such that massive connectivity is rendered.The expression allows for the development of simple yet successful interference suppression based on power allocation and phase shaping techniques that maximizes the sum rate since it is equivalent to fixed-point programming as can be proved.The proposed design is exemplified by nonlinear modulation schemes such as minimum shift keying(MSK)and Gaussian MSK(GMSK),two pivotal modulation formats in IoMT standards such as Link-16 and JITDS.Numerical results show that near capacity performance is offered.Fortunately,the performance is obtained using simple forward error corrections(FECs)of higher coding rate than existing schemes do,while the transmit power is reduced by 6 dB.The proposed design finds wide applications not only in IoMT but also in deep space communications,where ultra reliability and massive connectivity is a keen concern.

Performance improvement of licklider transmission protocol in complex deep space networks based on parameter optimization

A reasonable parameter configuration helps improve the data transmission performance of the Licklider Transmission Protocol(LTP).Previous research has focused mainly on parameter optimization for LTP in simplified scenarios with one to two hops or multihop scenarios with a custody mechanism of the Bundle Protocol(BP).However,the research results are not applicable to communications in Complex Deep Space Networks(CDSNs)without the custody mechanism of BP that are more suitable for deep space communications with LTP.In this paper,we propose a model of file delivery time for LTP in CDSNs.Based on the model,we propose a Parameter Optimization Design Algorithm for LTP(LTP-PODA)of configuring reasonable parameters for LTP.The results show that the accuracy of the proposed model is at least 6.47%higher than that of the previously established models based on simple scenarios,and the proposed model is more suitable for CDSNs.Moreover,the LTP parameters are optimized by the LTP-PODA algorithm to obtain an optimization plan.Configuring the optimization plan for LTP improves the protocol transmission performance by at least 18.77%compared with configuring the other parameter configuration plans.

广义确定性标识网络

随着智能制造、智能交通等重大国家战略实施,确定性成为信息网络尤其是行业专网的新焦点.现有确定性网络技术始终关注网络传输要素(带宽、时隙等)来保障数据流的确定性传输.然而,仅靠保障传输要素无法支撑新兴行业应用的多样化需求.例如,在算网融合场景,智算任务要求同时保障传输与计算要素的确定性来实现高性能通信;在绿色通信场景,需要考虑节点能量要素的确定性以维持网络稳定运行.针对上述需求,本文基于前期提出的标识网络技术,研究面向传输、计算、存储、能量等多要素的广义确定性网络.首先提出广义确定性标识网络架构,包括差异化服务层、异构融合网络层和智慧化适配层.差异化服务层和异构融合网络层,分别实现差异化确定性应用需求和异构化确定性网络要素的统一标识和描述,并通过标识解析映射实现确定性信息向智慧化适配层的统一封装和传递;智慧化适配层完成差异化确定性应用需求和异构化确定性网络要素的适配.现有确定性资源适配方法,即使仅考虑单一网络内的基本确定性要素,仍面临计算时间长、求解复杂性高、灵活度低等问题,为了支持更加复杂的多确定性要素、多种异构网络的协同适配,设计了基于深度强化学习的端到端的确定性调度(End-to-end Deterministic resource scheduling,E2eDet)算法,该算法可统一化、端到端地为混合数据流协同分配多种确定性网络资源,满足不同应用的差异化确定性需求.实验表明,E2eDet比DeepCQF和Random算法分别提升了28.4%和6.38倍数据流调度数量,同时E2eDet可以较好地权衡计算时间和调度能力.

深空探测自主运行的一种可信性技术体系

未认知与不确定性是深空探测任务的基本特征.本文基于战略导向的体系化基础研究,建立了一种面向科学价值最大化的探测场景和以可靠性为核心技术基础的深空探测自主运行可信性技术体系.分析研究了深空探测场景下的可靠性概念;面向精确感知、最优计算、准确决策、快精准执行的目标要素,提出了深空探测自主运行的可信性体系框架以及“需求-认知-工程”总体技术架构;针对自主运行可信性的关键技术难点,开展了可靠性导向的多物理场、强耦合白盒建模,复杂网络故障传播机制分析,COTS元器件深空探测应用的高可靠保证,以及“模型+数据+知识”一体的融合机制分析等研究.对该技术体系的关键技术验证策略及其最小系统在卫星星座中的应用进行了验证,结果表明,所提出的技术体系具有较高的工程价值.

基于K-means聚类和特征空间增强的噪声标签深度学习算法

深度学习中神经网络的性能依赖于高质量的样本,然而噪声标签会降低网络的分类准确率。为降低噪声标签对网络性能的影响,噪声标签学习算法被提出。该算法首先将训练样本集划分成干净样本集和噪声样本集,然后使用半监督学习算法对噪声样本集赋予伪标签。然而,错误的伪标签以及训练样本数量不足的问题仍然限制着噪声标签学习算法性能的提升。为解决上述问题,提出基于K-means聚类和特征空间增强的噪声标签深度学习算法。首先,该算法利用K-means聚类算法对干净样本集进行标签聚类,并根据噪声样本集与聚类中心的距离大小筛选出难以分类的噪声样本,以提高训练样本的质量;其次,使用mixup算法扩充干净样本集和噪声样本集,以增加训练样本的数量;最后,采用特征空间增强算法抑制mixup算法新生成的噪声样本,从而提高网络的分类准确率。并在CIFAR10、CIFAR100、MNIST和ANIMAL-10共4个数据集上试验验证了该算法的有效性。

基于深度强化学习的空天地一体化网络资源分配算法

空天地一体化网络(SAGIN)通过提高地面网络的资源利用率可以有效满足多种业务类型的通信需求,然而忽略了系统的自适应能力和鲁棒性及不同用户的服务质量(QoS)。针对这一问题,该文提出在空天地一体化网络架构下,面向城区和郊区通信的深度强化学习(DRL)资源分配算法。基于第3代合作伙伴计划(3GPP)标准中定义的用户参考信号接收功率(RSRP),考虑地面同频干扰情况,以不同域中基站的时频资源作为约束条件,构建了最大化系统用户的下行吞吐量优化问题。利用深度Q网络(DQN)算法求解该优化问题时,定义了能够综合考虑用户服务质量需求、系统自适应能力及系统鲁棒性的奖励函数。仿真结果表明,综合考虑无人驾驶汽车,沉浸式服务及普通移动终端通信业务需求时,表征系统性能的奖励函数值在2 000次迭代下,相较于贪婪算法提升了39.1%;对于无人驾驶汽车业务,利用DQN算法进行资源分配后,相比于贪婪算法,丢包数平均下降38.07%,时延下降了6.05%。

欧美月球GNSS规划现状分析综述

月球是地球最重要的天然卫星,当前国际上正在迎来新一轮月球探索高潮,数十个机构和商业团队正在规划月球探索任务,并设想在未来实现航天员长期驻月,围绕月球的“太空竞赛”刚刚开始。月球GNSS(基于现有的地球GNSS以及新的环月卫星通信导航基础设施的月球卫星通信导航定位技术)是空间基准科研的基础,能够提供航天器着陆定位以及月面(及其覆盖空间)定位、导航与授时等服务,同时可以将月球作为试验场,将导航工具包扩展到更远的目的地(如火星)。对欧美近期发布的月球GNSS规划进行了整理归纳,其中包括美国月球GNSS接收机实验(LuGRE)计划和欧洲月光(MoonLight)计划,以及美国中远期月球通信中继和导航系统(LCRNS)计划,这些计划可以为我国开展月球GNSS规划提供参考。

结合双曲图注意力网络与标签信息的短文本分类方法

针对现有方法在文本分类任务中没有综合考虑文本的层级结构和标签对于文本特征学习的重要性而导致的鲁棒性不足、表达能力不足等问题,提出了一种基于双曲图注意力网络的短文本分类算法L-HGAT。利用文本的复杂层级结构与双曲空间的树相似性特征的契合性,将文本嵌入到具有负常数曲率的双曲空间中,充分利用双曲流行表征的强大表达能力。设计双曲图注意力网络,融合节点特征与边特征,增强对文本中关键局部信息的聚合能力。使用基于双曲空间中的测地线距离的标签文本交互函数进一步引导文本特征学习,以此提升文本分类精度。实验结果表明,与基准模型相比,所提方法在基准数据集上显著优于现有研究方法,能够有效地提升模型性能,更好地完成文本分类任务。

基于应用场景的城市深部地下空间规划模式研究

地下空间开发利用是解决当前我国土地资源紧张、人口稠密、交通堵塞等诸多城市问题的一种重要途径,但当前浅层地下空间开发利用方式难以直接指导我国复杂的深地开发场景,探寻深地空间开发组织模式是我国新时期城市化发展的必然需求。通过梳理国内外深部地下空间应用场景,通过分析深地矿井、深地交通、深地储存、深地实验室等各类场景下相应空间特征以及使用需求等,总结提出了点状、线状、面状和立体网络式4种典型的深部地下空间网络组织模式,并分析4种典型发展模式的适用特征与可能的应用场景,以期为我国深地空间开发建设和场景设计提供参考借鉴。

深地空间长距离空气输送系统方案比较及优化研究

以某深地空间长距离送风系统为例,采用Ventsim软件计算了4种风量调节方案的系统风机风压与管道阻力的变化,提出了增加干管风机数量和改变进风竖井位置2种优化方法,分析了送风系统管网阻抗与等积孔面积的变化。结果表明,优化后送风系统的管网阻抗和等积孔面积分别最大降低0.102 kg/m^(7)和0.030 m^(2),科学的送风方案既能满足风量需求,又能降低长距离送风系统的阻力,具有较好的节能与经济效益。

空间无线光CDMA网络的探讨

通过对自由空通信中的多址环境空间无线光通信的强背景噪声等特点的分析以及对多种多址方式的对经，综合讨论自由空间无线光通信中采用码分多址技术的可行性、优越性和技术难点在此基础上。

基于知识融合和深度强化学习的智能紧急切机决策

紧急控制是在严重故障后维持电力系统暂态安全稳定的重要手段。目前常用的“人在环路”离线紧急控制决策制定方式存在效率不高、严重依赖专家经验等问题,该文提出一种基于知识融合和深度强化学习(deep reinforcement learning,DRL)的智能紧急切机决策制定方法。首先,构建基于DRL的紧急切机决策制定框架。然后,在智能体处理多个发电机决策时,由于产生的高维决策空间使得智能体训练困难,提出决策空间压缩和应用分支竞争Q(branching dueling Q,BDQ)网络的两种解决方法。接着,为了进一步提高智能体的探索效率和决策质量,在智能体训练中融合紧急切机控制相关知识经验。最后,在10机39节点系统中的仿真结果表明,所提方法可以在多发电机决策时快速给出有效的紧急切机决策,应用BDQ网络比决策空间压缩的决策性能更好,知识融合策略可引导智能体减少无效决策探索从而提升决策性能。

DMANet:针对空间非合作目标位姿估计的密集多尺度注意力网络

利用单目相机对空间非合作目标进行准确的姿态估计对于空间碎片清除、自主交会和其他在轨服务至关重要。然而,单目姿态估计方法缺乏深度信息,导致尺度不确定性问题,大大降低了其精度和实时性。本文首先提出了一种多尺度注意块(Multi-scale attention block, MAB),从输入图像中提取复杂的高维语义特征。其次,基于MAB模块,提出了空间非合作目标6自由度位姿估计的密集多尺度注意网络(Dense multi-scale attention network, DMANet),该网络由平面位置估计、深度位置估计和姿态估计3个分支组成,通过引入基于欧拉角的软分类方法,将位姿回归问题表述为经典分类问题。此外,设计了空间非合作目标模型,并利用Coppeliasim构建了姿态估计数据集。最后,与其他最先进的方法相比,在SPEED+、URSO数据集和本文数据集上全面评估了所提出的方法。实验结果表明,该方法具有较好的姿态估计精度。

深度融合频域和空间域特征的多粒度动态场景图像去模糊网络

动态场景下的图像去模糊具有高度的不适定性,相机与被拍摄目标之间的相对运动使模糊呈现非均匀性.现有深度学习方法大多集中于空间域而忽略频域对于结构及细节恢复的潜在贡献,导致去模糊效果欠佳.为了解决此问题,文中重新审视频域信息在图像去模糊中的作用,提出深度融合频域和空间域特征的多粒度动态场景图像去模糊网络.首先,提出频域门控的频空特征深度融合模块,充分挖掘空间域和频域信息间的相关性,减少融合后特征的冗余,增强两域之间的互补.然后,构建多粒度去模糊网络,充分利用空间域和频域中的不同粒度信息进行从粗到细的图像去模糊.最后,针对训练和测试时输入特征图尺寸不同导致的频域特征图分辨率不匹配问题,采用频域分辨率自适应的测试策略,保持频率变化的一致性.在合成数据集GoPro、HIDE和真实数据集RealBlur上的实验表明文中网络在重建清晰图像方面表现较优,同时参数量及效率具有一定的竞争力.

面向“CE-3号”软着陆过程的深空网干涉测量技术

针对"CE-3号"探测器软着陆过程中弹道位置测定的问题,利用中国深空网干涉测量测轨数据,论述并验证了应用深空网干涉测量技术支持探月卫星软着陆过程中弹道位置测定的可行性。针对提取同一时刻观测量的两个核心技术,论述了自适应模型重构算法以及干涉相位解模糊算法,克服了软着陆过程航天器机动不确定性恶化轨道预报精度,进而引起相关引导模型失效的问题;利用跟踪过程中目标干涉相位连续特性递推实现干涉相位解模糊。实测数据的处理分析表明,深空网干涉测量数据处理分析精度在0.3ns量级,对应于约30nrad的角位置精度。

基于DDQN改进方法的“斗地主”策略

基于当前一些已有方法在牌类博弈中训练时间长、动作空间大、胜率低等问题,提出了针对DDQN算法网络架构、编码方式的改进方法。采用二进制对手牌特征进行编码,采用手牌拆分的方法把神经网络分为主牌神经网络和副牌神经网络,并且增加GRU神经网络处理序列动作。经实验表明,该算法训练时间比传统DQN算法缩短了13%,在“地主”和“农民”位置上的平均胜率为70%和75%,高于DQN算法的28%和60%,证明了改进算法在上述部分指标方面的优势。