保证航电波分复用网络实时性的虚拓扑设计

针对航空电子波分复用网络消息的实时性要求,对航空电子网络的结构进行了研究,分析了在该网络中造成消息延迟的主要因素为转发延迟。进而对航空电子网络建模,根据WDM网络的资源特性进行拓扑的约束,提出了基于综合考虑虚拓扑跳数以及消息的带宽保证为目标的线性规划算法,在此基础上给出了大型网络的一个启发式算法,采用该线性规划算法对NSFNet网络拓扑进行了仿真验证。仿真结果表明,综合考虑虚拓扑跳数和消息带宽能减少消息的延迟,保证了网络实时性。     

一种基于用户终端协助的承载分离机制

针对第五代移动通信网络双连接架构中承载分离算法执行时间间隔过长降低分离算法性能的问题,提出了一种基于用户终端协助的承载分离机制。通过构建用户满意度模型,实时计算用户对网络的满意度,根据终端的用户实时满意度和实际数据接收比向主基站发送终端的反馈消息。主基站根据用户的反馈消息及时调整承载分离比例和切换终端的连接模式。该机制可以与现有的承载分离算法相结合。系统仿真结果表明,相对于传统的承载分离算法,该机制能够提升10%的用户满意度;在通信系统负载较大时,能够提升10%的系统总吞吐量。     

实时网络的分布式调度

针对主—从结构实时网络的性能特点,提出了一种基于EDF的主节点分布式实时任务调度算法,给出了该调度算法下实时任务组的可调度的充分条件。仿真测试表明,该调度算法满足实时约束,适合于主—从结构的实时网络调度。     

可重配置系统中的联合负载控制及其终端选择算法

该文基于现有端到端可重配置系统架构,提出了一种改进的动态门限联合负载控制方法,以适应不同负载条件下对负载均衡的要求,达到资源的有效利用。同时,结合终端的可重配置特点及业务要求的多样性,在执行网络发起的垂直切换过程中采用了基于层次分析法的终端选择算法,从而在均衡异构网络负载的同时减少系统开销和对用户的影响。仿真结果表明,该方法能够在保证用户满意度的同时有效地减轻重叠覆盖区域的网络拥塞,提高系统性能。     

FC—AE—ASM网络调度算法研究

FC—AE—ASM网络协议介绍了消息特征和网络结构,但没有规定消息的调度算法。确定一种能满足高实时性要求的调度算法是研究FC—AE—ASM网络的关键问题。该文提出了一种基于实时排队论的调度算法,建立了FC—AE—ASM的网络结构模型和数据模型．并推导出实时任务集可调度的充分必要条件。通过仿真分析,以消息传输的延时率为性能衡量指标,验证了该调度算法能很好满足消息传输的实时性要求。     

线性令牌传递网络在严格实时条件下的带宽分配方法

本文对线性令牌传递网络（ＬＴＰＢ）的实时特性进行了研究，提出了与节点负载匹配的网络带宽分配方法，导出了在该方法下网络消息集严格实时的充要条件，导出并证明了即使在最坏情况下消息集严格实时的网络可达负载率不小于５０％。     

一种改进的动态反馈负载均衡算法

在集群系统中,负载均衡算法是影响系统性能的关键因素之一.为了进一步提高集群系统的性能,有必要对负载均衡算法进行优化.通过对最小连接算法和DFB(Dynamic Feed-Back)算法的详细分析,提出了一种改进的动态反馈负载均衡算法.该算法通过收集每台服务器的实时性能参数,动态地计算出各服务节点的分配概率,并由此决定用户请求分配给哪一个服务节点.通过对上述三种算法性能的测试,得出了该算法能够有效提高集群系统性能的结论.     

一种混合WDM网络的实时传输策略

波分复用(Wavelength Division Multiplexing,WDM)网络应用于实时性网络环境的关键因素是实时传输策略。在混合式WDM网络结构中,研究了子网内的实时调度和子网间的路由策略。其中子网内为星形耦合式WDM网络,分析了区分丢弃-最早时限优先调度法(DDS-EATS)的不足,针对多消息多次调度的问题提出了改进方案。子网间网络采用洗牌型WDM波长路由网,消息路由采用轻载固定路由,重载流量疏导的方法。最后在OPNET仿真平台上,验证了该传输策略下消息的实时传输性能和多次消息调度中改进算法的网络延迟和网络利用率的网络性能。     

SuperPON的一个自适应带宽分配算法及其时延性能分析

针对SuperPON接入系统大时延、多用户的特点,给出了针对非实时业务流的基于申请-许可的带宽分配算法,自适应于网络的负载状况,申请信道动态地从随机接入到固定分配间切换.系统的时延特性由计算机模拟给出,结果表明该算法同时保证系统在低负载时的低时延特性和高负载时的高吞吐量,能改善尽力服务类型业务的性能.     

实时管理约束下节点级低功耗数据融合技术

通过对工业无线传感器网络中传感数据在时间维数据特征的研究,结合网络管理实时性的要求,提出了一种实时管理约束下节点级低功耗数据融合算法.该算法能实现网关对网络的实时管理,是一种有效地进行数据优化和管理的方式.理论分析和实验表明,该算法减少了数据发送的次数,节点的功耗减少了28%,提高了网络生命周期,并节省网络通信带宽.     

光纤通道仲裁环实时性能分析

光纤通道仲裁环(FC-AL)是光纤通道的基本拓扑结构之一。确保消息的实时传输是衡量系统实时性能的关键指标,网络带宽在节点间的合理分配是保证消息实时传输的重要原因。为了保证仲裁环在强实时环境下的应用,分析比较目前存在的一些带宽分配方法,最后验证了选择合适的带宽分配方法对提高仲裁环的实时性能起着关键作用。     

光谱干扰实时校正器的研究

复杂的光谱干扰限制了ICP-AES分析技术的进一步发展。最近提出的一些光谱干扰校正算法都因运算量大,而难以在一般微机上实时运行。本文基于算法和处理速度的综合考虑,采用VLSI数字信号处理器(DSP芯片)构成光谱干扰校正硬件与Shen Lansun(沈兰荪)等人(1989)提出的算法相结合,初步实现了对ICP-AES光谱干扰的实时校正,从而为光谱干扰实时校正的研究开辟了一条新路。     

无线传播信道回放模型建模方法及应用

介绍了一种确定性无线信道建模方法——回放模型建模方法，该方法以实时高速的实际无线传播环境测量为基础，能精确复制无线环境的传播特征。首先给出回放模型的建模思路以及对无线信道测量方法和测量仪器的要求：然后重点介绍处理实际外场测量数据形成回放模型的主要步骤和方法，并给出一些典型无线环境的测量和数据处理结果；实际测量和应用例子表明回放模型相对统计模型能更加精确的描述典型无线环境的传播特征，从而在WCDMA等无线系统尤其是物理层系统设计和优化过程中发挥重要的作用。     

Hardware-Software Partitioning for Real-Time Embedded Systems

In this paper, we present an approach to hardware-software partitioning for real-time embedded systems. Hardware and software components are modeled at the system level, so that cost and performance tradeoffs can be studied early in the design process and a large design space can be explored. Feasibility factor is introduced to measure the possibility of a real-time system being feasible, and is used as both a constraint and an attribute during the optimization process. An imprecise value function is employed to model the tradeoffs among multiple performance attributes. Optimal partitioning is achieved through the use of an existing computer-aided design tool. We demonstrate the application of our approach through the design of an example embedded system.     

Efficient Design of High-Capacity Dense Wavelength-Division Multiplex Systems

An efficient design methodology for high-capacity dense wavelength-division multiplexed systems is presented. In contrast to complex and time-consuming numerical simulations, analytical equations and heuristicapproximations are used to model the system performance. They facilitate first-order performance estimates and the identification of limiting effects even for multi-Tb/s systems within a few seconds.Taking into account local and accumulated group velocity dispersion, impairments due to fibre nonlinearities are described as a function of the average optical input power per channel. In combination with thedegradation of the optical signal-to-noise ratio caused by optical amplifier noise the maximum transmission distance versus optical input power can bedetermined.The validity of the models is verified by means of numerical simulations and system experiments. The dependence on data rate, modulation format, fibre type and dispersion compensation scheme is determined. Practical examples illustrate the usefulness of our design approach.     

Design optimization of low-power high-performance DSP building blocks

In recent years, power dissipation along with silicon area has become the key figure in chip design. The increasing demands on system performance require high-performance digital signal processing (DSP) systems to include dedicated number-crunching units as individually optimized building blocks. The various design methodologies in use stress one of the following figures: power dissipation, throughput, or silicon area. This paper presents a design methodology reducing any combination of cost drivers subject to a specified throughput. As a basic principle, the underlying optimization regards the existing interactions within the design space of a building block. Crucial in such optimization is the proper dimensioning of device sizes in contrast to the common use of minimal dimensions in low-power implementations. Taking the design space of an FIR filter as an example, the different steps of the design process are highlighted resulting in a low-power high-throughput filter implementation. It is part of an industrial read-write channel chip for hard disks with a worst case throughput of 1.6 GSamples/s at 23 mW in a 0.13-/spl mu/m CMOS technology. This filter requires less silicon area than other state-of-the-art filter implementations, and it disrupts the average trend of power dissipation by a factor of 6.     

基于阵列单通道的机动目标DOA跟踪方法

针对现有利用阵列单通道系统对机动目标跟踪精度不高,实时性差等不足,提出了一种新的基于改进粒子滤波算法的阵列单通道机动目标波达方向(direction of arrival, DOA)跟踪方法。该方法首先在利用接收机轮流采样建立数学模型的基础上,建立跟踪模型。然后,利用粒子群优化算法对马尔科夫链蒙特卡罗(Markov Chain Monte Carlo, MCMC)粒子滤波算法的重采样环节进行优化处理,给出了一种交互MCMC粒子滤波算法,该算法克服了传统粒子滤波算法粒子退化及样本贫化的固有缺陷。最后利用该算法求解跟踪方程,实现了实时DOA估计。理论分析与仿真结果表明,本文方法可实现基于阵列单通道的DOA跟踪与波束形成一体化,且能够处理相干信号,与标准粒子滤波和子空间类算法相比,收敛速度快,跟踪精度高。      

A low-cost cellular mobile communication system: a hierarchicaloptimization network resource planning approach

This paper deals with the optimization of the design and radio network resource planning for cellular mobile communication systems. The key element to be considered for mobile network planning is cost. A hierarchical optimization planning method (HOP) is utilized since there are so many factors like system performance, terrain features, base station parameters, and cost factors which are involved in the large-scale system design. We present a three-level optimization approach for designing a cellular mobile system. It determines the cell number, cell site allocation, and the specific base station parameters in order to minimize the total system cost and to comply with the required system performance. The problem is formulated as a large combinatorial optimization model which can determine the optimal number of cells and select the best base stations' locations. The simulated annealing approach is developed to solve the hard combinatorial problem. Simulation results demonstrate the feasibility and effectiveness of the HOP approach for radio network planning     

容错轮询系统分析模型

本文提出的多服务器轮询系统分析模型考虑了故障对系统性能的影响,特别适应于在任务级或传输子系统级评估分布式实时系统的响应特性,对容错分布式系统设计及系统重组策略的优化、选择具有指导意义。