Research and Progress of Service Driven Optical Switching Network in China

National R&D activities on optical switching networkare introduced. Optical switching network testbedswere established in China including 3T-net andOBS ring and mesh network test-bed with the supportof national '863' program. As an importantmodule in OPS network, a novel all-optical serialmulticast mode is discussed.

Machine Learning for 5G and Beyond:From ModelBased to Data-Driven Mobile Wireless Networks

During the past few decades,mobile wireless communications have experienced four generations of technological revolution,namely from 1 G to 4 G,and the deployment of the latest 5 G networks is expected to take place in 2019.One fundamental question is how we can push forward the development of mobile wireless communications while it has become an extremely complex and sophisticated system.We believe that the answer lies in the huge volumes of data produced by the network itself,and machine learning may become a key to exploit such information.In this paper,we elaborate why the conventional model-based paradigm,which has been widely proved useful in pre-5 G networks,can be less efficient or even less practical in the future 5 G and beyond mobile networks.Then,we explain how the data-driven paradigm,using state-of-the-art machine learning techniques,can become a promising solution.At last,we provide a typical use case of the data-driven paradigm,i.e.,proactive load balancing,in which online learning is utilized to adjust cell configurations in advance to avoid burst congestion caused by rapid traffic changes.

EARS: Intelligence-Driven Experiential Network Architecture for Automatic Routing in Software-Defined Networking

Software-Defined Networking(SDN)adapts logically-centralized control by decoupling control plane from data plane and provides the efficient use of network resources.However,due to the limitation of traditional routing strategies relying on manual configuration,SDN may suffer from link congestion and inefficient bandwidth allocation among flows,which could degrade network performance significantly.In this paper,we propose EARS,an intelligence-driven experiential network architecture for automatic routing.EARS adapts deep reinforcement learning(DRL)to simulate the human methods of learning experiential knowledge,employs the closed-loop network control mechanism incorporating with network monitoring technologies to realize the interaction with network environment.The proposed EARS can learn to make better control decision from its own experience by interacting with network environment and optimize the network intelligently by adjusting services and resources offered based on network requirements and environmental conditions.Under the network architecture,we design the network utility function with throughput and delay awareness,differentiate flows based on their size characteristics,and design a DDPGbased automatic routing algorithm as DRL decision brain to find the near-optimal paths for mice and elephant flows.To validate the network architecture,we implement it on a real network environment.Extensive simulation results show that EARS significantly improve the network throughput and reduces the average packet delay in comparison with baseline schemes(e.g.OSPF,ECMP).

Artificial Intelligence-Driven Fog-Computing-Based Radio Access Networks

The edge cache is an effective way to reduce the heavy traffic load and the end-to-end latency in radio access networks(RANs)for supporting a number of critical Internet of Things(IoT)services and applications.It has been verified to provide high spectral efficiency,high energy efficiency,and low latency.To exploit the advantages of edge cache,a paradigm of fog computing-based radio access networks(F-RANs)has emerged to provide great flexibility to satisfy quality-of-service requirements of various IoT applications in the fifth generation(5G)wireless systems.

Study on limited-flux coefficient to achieve spare transportation of heat-supply network

Limited-heating is one of the heating statuses which can meet the reliability requirement of those uninterrupted heat-users under the accidental status of heat-supply network.It requires the network to be provided with both ability of spare-structure and spare-transportation,and the later one is depended on the limited-flux coefficient.This paper investigates the relationship between the limited-flux coefficient and limited-heating coefficient of indirect connection system.The optimal value of the limited-flux coefficient is presented as well.

Revisiting the Outsiders: Innovative Recruitment of a Marijuana User Network via Web-Based Respondent Driven Sampling

This study uses an innovative, network-based recruitment strategy (non-monetary, web-based respondent driven sampling) to gather a sample of il/legal marijuana users. Network-driven effects amongst marijuana users are examined to test the explanatory validity of several theories of social deviance. The study finds that respondent driven sampling techniques lack effectiveness without primary monetary incentives, even when meaningful secondary incentives are utilized. Additionally, the study suggests that marijuana user networks exhibit strong homophilic attachment tendencies.

A deep learning driven hybrid beamforming method for millimeter wave MIMO system

The hybrid beamforming is a promising technology for the millimeter wave MIMO system,which provides high spectrum efficiency,high data rate transmission,and a good balance between transmission performance and hardware complexity.The most existing beamforming systems transmit multiple streams by formulating multiple orthogonal beams.However,the Neural network Hybrid Beamforming(NHB)adopts a totally different strategy,which combines multiple streams into one and transmits by employing a high-order non-orthogonal modulation strategy.Driven by the Deep Learning(DL)hybrid beamforming,in this work,we propose a DL-driven nonorthogonal hybrid beamforming for the single-user multiple streams scenario.We first analyze the beamforming strategy of NHB and prove it with better Bit Error Rate(BER)performance than the orthogonal hybrid beamforming even with the optimal power allocation.Inspired by the NHB,we propose a new DL-driven beamforming scheme to simulate the NHB behavior,which avoids time-consuming neural network training and achieves better BERs than traditional hybrid beamforming.Moreover,our simulation results demonstrate that the DL-driven nonorthogonal beamforming outperforms its traditional orthogonal beamforming counterpart in the presence of subconnected schemes and imperfect Channel State Information(CSI).

An artificial viscosity augmented physics-informed neural network for incompressible flow

Physics-informed neural networks(PINNs)are proved methods that are effective in solving some strongly nonlinear partial differential equations(PDEs),e.g.,Navier-Stokes equations,with a small amount of boundary or interior data.However,the feasibility of applying PINNs to the flow at moderate or high Reynolds numbers has rarely been reported.The present paper proposes an artificial viscosity(AV)-based PINN for solving the forward and inverse flow problems.Specifically,the AV used in PINNs is inspired by the entropy viscosity method developed in conventional computational fluid dynamics(CFD)to stabilize the simulation of flow at high Reynolds numbers.The newly developed PINN is used to solve the forward problem of the two-dimensional steady cavity flow at Re=1000 and the inverse problem derived from two-dimensional film boiling.The results show that the AV augmented PINN can solve both problems with good accuracy and substantially reduce the inference errors in the forward problem.

Assessment of Random Recruitment Assumption in Respondent-Driven Sampling in Egocentric Network Data

One of the key assumptions in respondent-driven sampling (RDS) analysis, called “random selection assumption,” is that respondents randomly recruit their peers from their personal networks. The objective of this study was to verify this assumption in the empirical data of egocentric networks. Methods: We conducted an egocentric network study among young drug users in China, in which RDS was used to recruit this hard-to-reach population. If the random recruitment assumption holds, the RDS-estimated population proportions should be similar to the actual population proportions. Following this logic, we first calculated the population proportions of five visible variables (gender, age, education, marital status, and drug use mode) among the total drug-use alters from which the RDS sample was drawn, and then estimated the RDS-adjusted population proportions and their 95% confidence intervals in the RDS sample. Theoretically, if the random recruitment assumption holds, the 95% confidence intervals estimated in the RDS sample should include the population proportions calculated in the total drug-use alters. Results: The evaluation of the RDS sample indicated its success in reaching the convergence of RDS compositions and including a broad cross-section of the hidden population. Findings demonstrate that the random selection assumption holds for three group traits, but not for two others. Specifically, egos randomly recruited subjects in different age groups, marital status, or drug use modes from their network alters, but not in gender and education levels. Conclusions: This study demonstrates the occurrence of non-random recruitment, indicating that the recruitment of subjects in this RDS study was not completely at random. Future studies are needed to assess the extent to which the population proportion estimates can be biased when the violation of the assumption occurs in some group traits in RDS samples.

Information-Driven Collaborative Processing for Diffusive Source Estimation in Wireless Sensor Networks

This paper discusses an accurate distributed algorithm for diffusive source localization while maintaining the low energy consumption of sensor nodes in wireless sensor networks. In this algorithm, the sensor selection scheme based on the information utility measure is used. To update the estimation in each selected node, a neighborhood radius equal to the communication range of the sensor nodes is defined and all sensors located in the neighborhood circle, whose radius is equal to the neighborhood radius and the selected node is its centre, collaborate their information. To decrease the energy consumption, the neighborhood radius is reduced gradually based on the error covariance value of the estimation. In addition, this paper includes a new method for the initial point calculation which is important in the recursive methods used for distributed algorithms in wireless sensor networks. Numerical examples are used to study the performance of the algorithms. Simulation results show the accuracy of the new algorithm becomes better while its energy consumption is low enough.

支撑新型配电网数字化规划的图形⁃模型⁃数据融合关键技术

配电网规划领域期盼实现智能规划,其愿景在于实现无人或少人干预的全自动规划。在数字化转型的背景下,新型配电网规划将面临图形多样化、场景碎片化、数据规模化三大挑战。文中从图形-模型-数据融合的角度提出三大关键技术:基于电气图纸识别和拓扑智能分析的图形-模型融合技术、基于知识驱动的负荷/新能源推演分析和智能决策的模型-数据融合技术、基于多模态数据融合和多时空数据联动的图形-数据融合技术,尝试打破理论研究与数字化工程的壁垒。最后,对未来新型配电网数字化规划的发展进行思考和展望,为实现“以机为主,人机协同”的大闭环模式提供借鉴。

基于多域物理信息神经网络的复合地层隧道掘进地表沉降预测

复合地层中盾构掘进诱发地表沉降的准确预测是隧道工程安全建设与施工决策的关键问题。基于隧道施工诱发地层变形机制构建隧道收敛变形与掘进位置的联系,并将其耦合至深度神经网络(deep neural network,简称DNN)框架,建立了预测盾构掘进诱发地层变形的物理信息神经网络(physics-informed neural network,简称PINN)模型。针对隧道上覆多个地层的地质特征,提出了多域物理信息神经网络(multi-physics-informed neural network,简称MPINN)模型,实现了在统一的框架内对不同地层的物理信息分区域表达。结果表明:MPINN模型高度还原了有限差分法的计算结果,可以准确预测复合地层中隧道开挖诱发的地表沉降;由于融入了物理机制,MPINN模型对隧道施工诱发地表沉降的问题具有普适性,可应用于不同地质和几何条件下隧道诱发地表沉降的预测;基于工程实测数据,提出的MPINN模型准确预测了监测断面的地表沉降曲线,可为复合地层下盾构掘进过程中地表沉降的预测预警提供参考。

考虑大规模风光分层接入的配电网多层协调无功优化方法

大量风光新能源分层、多点接入给配电网运行带来了电压越限等负面影响,增加了不同电压等级无功协同优化的难度。兼顾不同电压等级调节需求,从模型降维等值的角度,提出了基于等值模型的配电网多层协调无功优化方法。该方法分别针对含有无功调节设备及没有无功调节设备的两种台区系统,利用神经网络对大量台区相关运行数据进行训练得到台区拟合模型,形成不可控和可控两种类型的台区等值模型,并用这两类拟合模型分别代替两类台区系统的物理模型,使台区以数据驱动的方式参与配电网无功优化,形成馈线物理模型和台区拟合模型组成的单一电压等级物数混合优化调度模型。将原多层无功优化问题转换为单层系统优化问题,再对该单层系统无功优化调度问题进行求解。该方法可降低配电网系统优化计算规模,从而减小计算量,以无功优化数学模型与数据驱动方法相结合的方式,实现配电网馈线-台区多层协调无功优化。通过算例验证了所提方法对于解决分布式风光分层接入所导致电压越限问题的可行性、有效性和优越性,能够保障配电网的经济安全稳定运行。

基于数据驱动贝叶斯网络的化工事故风险分析

为减少化工厂风险分析中的主观干预,基于关联规则和贝叶斯网络构建1种数据驱动风险分析模型。该模型涵盖3个任务项,分别为数据集项、关联规则驱动项和贝叶斯网络风险评估项。首先,收集事故报告和事故因素构建事故数据库;其次,将事故数据导入Apriori算法,并根据关联规则的因素相关性确定贝叶斯网络和条件概率表结构;然后,基于事故因素出现频率计算先验概率和条件概率,并采用Fussel-Vesely计算事故因素的敏感度;最后,收集94起危险化学品中毒窒息事故实例,运用数据驱动风险分析模型评估事故因素的影响大小。研究结果可为减少和避免化工事故提供一定参考,有助于提高相关企业的整体安全水平。

基于神经算子与类物理信息神经网络智能求解新进展

深度学习通过多层神经网络对数据进行学习,不仅能揭示潜藏信息,还能很好地解决复杂非线性问题.偏微分方程(PDE)是描述自然界中许多物理现象的基本数学模型.两者的碰撞与融合,产生了基于深度学习的PDE智能求解方法,它具有高效、灵活和通用等优点.文章聚焦PDE智能求解方法,以是否求解单一问题为判定依据,把求解方法分为两类:神经算子方法和类物理信息神经网络(PINN)方法,其中神经算子方法用于求解一类具有相同数学特征的PDE问题,类PINN方法用于求解单一问题.对于神经算子方法,从数据驱动和物理约束两个方面展开介绍,分析研究现状并指出现有方法的不足.对于类PINN方法,首先介绍了基础PINN的3种改进方法 (基于数据优化、基于模型优化和基于领域知识优化),然后详细介绍了基于物理驱动的两类解决方案:基于传统PDE离散方程的智能求解方案和无网格的非离散求解方案.最后总结技术路线,探讨现有研究存在的不足,给出可行的研究方案.最后,简要介绍智能求解程序发展现状,并对未来研究方向给出建议.

状态依赖型切换系统的数据驱动方法建模

切换系统是由一系列连续或离散的子系统和切换机制组合而成的一类复杂系统,状态依赖型切换系统因其复杂性而尚未被深入研究.因此,通过系统的输入输出轨迹来对状态依赖的切换系统进行数据驱动建模,利用数据挖掘技术寻找数据之间的有用信息,建立输入与输出之间更形象的表达形式;在此基础上提出一种结构框架,根据辨识轨迹的切换时刻将数据分段,借助神经网络建立子系统的模型以及切换规则,深度挖掘状态依赖切换系统的信息,得到切换系统中子系统及子系统间的信息.实验结果表明:相比传统的机理建模,本文提出的数据驱动方法将建模的复杂度降低了17.3%.

数据驱动的半无限介质裂纹识别模型研究

缺陷识别是结构健康监测的重要研究内容,对评估工程结构的安全性具有重要的指导意义,然而,准确确定结构缺陷的尺寸十分困难.论文提出了一种创新的数据驱动算法,将比例边界有限元法(scaled boundary finite element methods,SBFEM)与自编码器(autoencoder,AE)、因果膨胀卷积神经网络(causal dilated convolutional neural network,CDCNN)相结合用于半无限介质中的裂纹识别.在该模型中,SBFEM用于模拟波在含不同裂纹状缺陷半无限介质中的传播过程,对于不同的裂纹状缺陷,仅需改变裂纹尖端的比例中心和裂纹开口处节点的位置,避免了复杂的重网格过程,可高效地生成足够的训练数据.模拟波在半无限介质中传播时,建立了基于瑞利阻尼的吸收边界模型,避免了对结构全域模型进行计算.搭建了CDCNN,确保了时序数据的有序性,并获得更大的感受野而不增加神经网络的复杂性,可捕捉更多的历史信息,AE具有较强的非线性特征提取能力,可将高维的原始输入特征向量空间映射到低维潜在特征向量空间,以获得低维潜在特征用于网络模型训练,有效提升了网络模型的学习效率.数值算例表明:提出的模型能够高效且准确地识别半无限介质中裂纹的量化信息,且AE-CDCNN模型的识别效率较单CDCNN模型提高了约2.7倍.

面向任务的无人飞行器自组网OLSR协议

无人飞行器(unmanned aerial vehicle,UAV)自组网的路由研究多以性能指标出发、忽略无人飞行器网络的任务驱动性,与实际需求动态耦合弱、适用性不强。针对该问题基于无人飞行器多任务网络提出了面向任务的无人飞行器联盟组网架构,提出了无人飞行器联盟的任务自适应优化链路状态路由协议(task adaptive optimized link state routing,TA-OLSR)。基于模糊逻辑设计拓扑稳定度计算方法,利用拓扑稳定度实现TA-OLSR控制消息的自适应广播,同时结合稳定度设计新的多点中继选择策略。仿真结果表明,TA-OLSR算法能从宏观面向任务的角度出发,实现不同任务下的良好自适应性,提升数据包投递率,减少冗余信息传播,降低网络开销,有效提高整体网络性能。

基于专家知识与监测数据联合驱动的高压开关柜状态评估

高压开关柜(HVS)作为电力系统的关键设备,对其工作状况进行有效评估可以保障电力系统的安全稳定运行。在工程实践中,由于高压开关柜长期服役于潮湿、高温等恶劣环境下,不可避免的传感器失效或人为因素会导致其设备状态数据存在随机缺失的现象,从而破坏了数据的完整性和可用性,使得对数据质量要求较高的数据驱动方法难以直接用于解决高压开关柜状态评估的问题。为了解决上述问题,研究了一种基于专家知识和监测数据联合驱动的高压开关柜状态评估方法。首先,对高压开关柜系统的内部构成进行了深入分析,并根据区域中设备的功能不同将其分为电缆室、母线室和断路器室三大区域。其次,进一步分析了系统状态、各区域状态及其关键部件状态两两之间的因果关系,从而建立了适用于高压开关柜状态评估的三层贝叶斯网络(BN)拓扑结构。然后,引入专家领域知识设计了适用于高压开关柜系统的3种约束罚函数,并通过求解带有约束的优化问题,改善了不完整数据集下的贝叶斯网络参数估计性能,进而实现了对高压开关柜系统状态的精确评估。最后,在自主设计的10 kV高压开关柜样机上开展了对比验证实验,结果表明,相比于支持向量机(SVM)方法和反向传播(BP)神经网络方法,本文所提方法在状态评估精度上更具优势。

基于LDA-BP神经网络的高校思政课教师数据驱动决策力评价研究

数据驱动决策力为高校思政课教师提供科学合理的教学判断,对数据驱动决策力进行评价研究,有助于提高高校思政课教师的数据决策水平,进而提升思想政治教育教学质量。鉴于传统评测方法缺乏客观性与可重复性,运用LDA-BP神经网络技术构建高校思政课数据驱动决策力的指标体系与评价模型。首先,运用LDA方法对高校思想政治教育相关的政策文本与研究文献进行主题提取,并将主题信息作为指标构建基础;其次,通过研读文献与政策文本,并结合主题分析结果构建高校思政课教师数据驱动决策力评价指标体系;最后,通过对BP神经网络的训练及测试来生成高校思政课教师数据驱动决策力的评价模型。研究表明,高校思政课教师的专业知识、教学水平以及数据分析与解读能力是影响数据驱动决策能力的关键因素,据此,理应从素养提升、文化培育、管理革新、政府支持等方面入手增强数据驱动决策力。