基于LS-SVM的光刻过程R2R预测控制方法

针对光刻过程非线性、时变和产品质量不易在线测量的特性,提出了一种基于最小二乘支持向量机预测模型和微粒群滚动优化方法的批次控制预测控制器。通过历史批次样本数据构建光刻过程的最小二乘支持向量机预测模型,解决了复杂光刻过程难以建立精确数学模型的难题,提高了预测模型的精度。通过预测误差的反馈校正和微粒群滚动优化算法求解最优控制律,提高了控制精度。性能分析结果表明,与指数加权移动平均方法及非线性模型预测控制方法相比较,批次控制预测控制器控制器减小了不同批次关键尺寸输出的差异,显著降低了关键尺寸输出的均方根误差,有效抑制了过程扰动影响。     

城域网BoD业务实现研究

按需带宽（BoD）是运营商将在未来新型城域网上开展的极具竞争力的个性化增值业务之一.首先概述了未来新型城域网的需求以及BoD业务的产生,然后对BoD业务的特点以及实现机制进行了一定的分析,再对城域网BoD业务的实现就集中式和分布式两种控制体系分别进行了较为详细的分析,最后总结了城域网BoD业务的优势及发展前景.     

ASON中BoD业务的实现

BoD业务是ASON提供的一种可以对业务带宽进行实时调整的新型业务.本文分析了其业务价值、实现模型、实现方式,并对BoD业务的计费和提供策略进行了研究.     

宽带接入网支持按需带宽业务及动态QoS的研究

宽带网络所承载的业务正从以传统互联网业务为主逐步向多业务承载方向发展，宽带接入网络必须实施网络转型以适应市场需求的变化和业务发展的需求。本文对按需带宽分配（BoD）业务以及BoD业务在宽带接入中的QoS需求进行了分析和研究，并进一步提出了在接入网内实施动态QoS々策略。     

EV-DO网络承载小流量长在线业务的性能分析及优化

分析了小流量长在线业务对EV-DO网络的影响,同时提出了一种业务接入控制的数学模型。通过仿真,得出了DO网络承载小流量长在线业务的网络性能优化方法,该优化方法能提升无线网络性能,接入更多用户。并从终端、网络、业务平台各个环节提出专为小流量长在线业务而优化的解决方案。     

室内噪声环境下气味源的多机器人微粒群搜索方法

针对室内噪声环境下的气味源定位问题,提出一种基于骨干微粒群进化的多机器人协调搜索方法.该方法将每个机器人看作一个微粒,机器人传感器探测到的气味浓度值作为微粒的适应值,所有机器人组成一个进化微粒群;采用动态统计方法在线估计机器人所测气味浓度的噪声强度,并通过区间数表示噪声环境下微粒的适应值;定义微粒间的概率支配关系,更新微粒的全局和局部引导者,并利用关于全局引导者和局部引导者的高斯采样更新机器人的位置.最后,通过2个典型实验环境,验证了所提算法在处理噪声环境下气味源定位问题的优越性.     

基于多目标微粒群优化的异质数据特征选择

环境和测量仪器精度的影响,使得采样数据的不同特征具有不同的质量.对这类异质数据进行特征选择,需要同时考虑特征子集确定分类器的准确度和可靠性,从而增加了特征选择的难度.本文研究异质数据的特征选择问题,提出一种基于多目标微粒群优化的特征选择方法.该方法首先以特征选择的概率为决策变量,将具有离散变量的特征选择问题,转化为连续变量多目标优化问题;然后,采用微粒群优化求解时,基于高斯采样,产生微粒的全局引导者,以提高Pareto解集的分布性;最后,依据储备集中元素更新的速度,确定需要扰动的微粒,以帮助微粒群跳出局部最优.将所提方法应用于多个典型数据集分类问题,实验结果表明了所提方法的有效性.     

基于机器学习的无线网络流量预测与增长潜力评估

提出一个基于机器学习的无线网络流量预测及流量增长潜力评估方案。该方案分析蜂窝网络中的实际业务流量数据在时间维度上的变化规律,并借助高斯过程的机器学习方法来预测业务变化趋势,从短期角度为运营商的网络优化部署提供指导。基于极限梯度提升(XGBoost)机器学习框架,建立网络中其他运营数据与业务流量的多维映射关系,应用改进的量子粒子群算法进一步寻找蜂窝小区所能承载的流量上限,从长期角度为网络优化部署提供指导,提升网络流量水平、释放流量增长潜力。     

基于微粒群改进BP算法的非线性方程PID参数整定研究

文章从微粒群算法和BP神经网络基本原理出发,研究了将其用于PID控制的可行性,实现参数的在线自整定。仿真结果表明。基于微粒群优化BP神经网络的非线性PID参数自整定取得了良好的控制效果。     

一种新型的神经网络预测控制方法

预测控制算法的核心是预测过程中的滚动优化,滚动优化方法选择是确定其是否实用的关键,针对这一特点,在此提出了一种以径向基函数（RBF）神经网络为多步预测模型的非线性预测控制算法。算法采用RBF神经网络建立系统预测模型,并以微粒群优化（PSO）算法作为滚动优化算法,用来实现在有限时域内对控制序列的寻优,提高了优化过程的收敛性和求解精度。仿真结果表明了算法的有效性和高效性,获得了良好的控制效果。     

OXC port dimensioning strategies in optical networks-a nodal perspective

In this letter, we investigate optical cross-connect (OXC) port dimensioning strategies for supporting bandwidth-on-demand (BoD) services in optical networks. At a given node, the bandwidth-on-demand traffic load consists of two components; an access component, which is generated by demands originating at that node, and a transit component, which is generated by demands that transit electronically through the node. Given the BoD load at a node, as well as a target BoD average blocking probability, we calculate the optimal static allocation of the OXC ports between client-side ports and network-side ports. We also introduce a dynamic sharing strategy of the network-side ports and propose a method for determining the optimal port allocation under this strategy.     

Design of versatile academic infrastructure for multilayer network services

This paper describes the network design and configurations of the new Japanese academic infrastructure, called SINET3, which provides a rich variety of network services to more than 700 universities and research institutions. Since the start of full-scale operations in June 2007, the network has expanded its services to include multi-layer transfer services (IP, Ethernet, and layer-1), enriched virtual private network services (L3VPN, L2VPN, VPLS, and L1VPN), enhanced QoS services (packet-based and circuit-based), and brand-new layer-1 bandwidth-on-demand (BoD) services. This paper explains how the network provides these various network services on a single network platform by effectively configuring leading-edge networking components, such as high-performance IP routers, layer- 1 switches, and a BoD server. Evaluations of the network design and configurations confirmed that the networking functions were effectively coordinated. The procedures and techniques related to the configuration validation that covered all phases of the network design and construction are also presented.     

A bandwidth-on-demand strategy for GPRS

General packet radio service (GPRS) is a global system for mobile communications (GSM) packet data service. In order to efficiently accommodate GPRS traffic while maintaining the desired service quality of GSM calls, we propose a GPRS bandwidth-allocation strategy called the bandwidth-on-demand (BoD) strategy. The BoD strategy is adaptive to the change of traffic conditions, and thus can dynamically adjust the number of channels for GSM and GPRS traffic. Taking the effect of packet dropping due to movements of mobile stations into account, this paper develops an analytical model to study the BoD performance in terms of GSM-call-blocking probability and GPRS-packet-dropping probability.     

Providing differentiated service to TCP flows over bandwidth on demand geostationary satellite networks

The elasticity of transmission control protocol (TCP) traffic complicates attempts to provide performance guarantees to TCP flows. The existence of different types of networks and environments on the connections' paths only aggravates this problem. In this paper, simulation is the primary means for investigating the specific problem in the context of bandwidth on demand (BoD) geostationary satellite networks. Proposed transport-layer options and mechanisms for TCP performance enhancement, studied in the single connection case or without taking into account the media access control (MAC)-shared nature of the satellite link, are evaluated within a BoD-aware satellite simulation environment. Available capabilities at MAC layer, enabling the provision of differentiated service to TCP flows, are demonstrated and the conditions under which they perform efficiently are investigated. The BoD scheduling algorithm and the policy regarding spare capacity distribution are two MAC-layer mechanisms that appear to be complementary in this context; the former is effective at high levels of traffic load, whereas the latter drives the differentiation at low traffic load. When coupled with transport layer mechanisms they can form distinct bearer services over the satellite network that increase the differentiation robustness against the TCP bias against connections with long round-trip times. We also explore the use of analytical, fixed-point methods to predict the performance at transport level and link level. The applicability of the approach is mainly limited by the lack of analytical models accounting for prioritization mechanisms at the MAC layer and the nonuniform distribution of traffic load among satellite terminals.     

最小二乘支持向量机在线建模在预测控制中的应用

针对智能预测控制中的预测模型,提出了最小二乘支持向量机(LS-SVM)在线模型的递推算法,减少了矩阵求逆计算。当模型达到较高的精度后,每次迭代过程中当一个新的数据点加入到数据集,则把具有最小|αi|的数据点删除。不但解决了数据集规模的问题,而且提高了预测模型的精确性。通过仿真验证了基于在线LS-SVM模型的预测控制可以使系统快速、准确地跟踪期望输出,达到预期的控制效果。     

MSTP的新业务及其应用

城域网正在从单纯的传送网向业务网演进,需要新的传送平台的支持.文章分析了基于SDH平台的多业务传送平台(MSTP)提供新业务的原理,并介绍了MSTP上的各种应用,认为融合虚容器(VC)级联、链路容量调整(LCAS)和通用成帧规程(GFP)等相关技术的多业务传送平台(MSTP),可以实现多种业务的综合接入和汇聚;由于MSTP可以内嵌弹性分组环(RPR)、多协议标签交换(MPLS)等技术,因此可以支持如虚拟专用网(VPN)和按需带宽(BoD)等新业务,并适应未来3G业务的发展.     

基于EPON的带宽管理系统

基于以太网无源光网络(EPON)接入的按需分配带宽技术,结合EPON硬件的多逻辑链路技术和网管的带宽管理功能,提出了带宽模板的机制,并通过研发EPON带宽管理系统,实现了基于模板时间表驱动的带宽按需分配.文章对带宽管理系统的总体架构设计和功能实现进行了论述,并用测试结果验证了系统的设计目标.     

一种适合宽带多媒体卫星通信系统的异步突发时间计划生成方法

 在宽带多媒体卫星通信系统带宽按需分配(Bandwidth on Demand,BoD)过程中,采用周期性突发时间计划生成(Periodical Burst Time Plan Generation,P-BTPG)方法会导致BoD性能对带宽分配周期和带宽分配时延十分敏感.通过建立BoD时序模型,推导最优带宽分配周期和分配时延值,给出一种最优的突发时间计划生成(Optimal Burst Time Plan Generation,O-BTPG)方法.针对该方法导致突发时间计划(Burst Time Plan BTP)信令开销过大的问题,进一步提出一种能够根据带宽需求异步生成突发时间计划(Asynchronous Burst Time Plan Generation,A-BTPG)的方法,推导采用该方法的最优带宽分配长度和最优带宽分配时刻表达式,给出该方法的执行流程;采用两种典型带宽分配算法对不同的BTP生成方法进行性能仿真与分析,仿真结果表明:A-BTPG方法具有较好的通用性,在控制BTP信令开销的前提下能够明显提升系统带宽动态响应能力.     

虚级联信号的链路容量调整机制LCAS及其在新一代SDH智能带宽响应中的应用

通用成帧规程GFP、VC虚级联和链路容量调整机制LCAS是有效实现Data over SDH(DoS)的新型协议。基于此运营商可以实现网络带宽的动态分配响应。通过分析LCAS的特点、结构和功能实现方式,指出其作为一种源-宿之间无损伤的改变虚级联组容量大小的握手信令协议,其服务可以建立在集中或分布式控制基础上。特别分析了结合基于GMPLS/ASTN的智能化控制平面,LCAS将进一步拓展BoD应用。