Hashed and hierarchical timing wheels: efficient data structuresfor implementing a timer facility

The performance of timer algorithms is crucial to many network protocol implementations that use timers for failure recovery and rate control. Conventional algorithms to implement an operating system timer module take O(n) time to start or maintain a timer, where n is the number of outstanding timers: this is expensive for large n. This paper shows that by using a circular buffer or timing wheel, it takes O(1) time to start, stop, and maintain timers within the range of the wheel. Two extensions for larger values of the interval are described. In the first, the timer interval is hashed into a slot on the timing wheel. In the second, a hierarchy of timing wheels with different granularities is used to span a greater range of intervals. The performance of these two schemes and various implementation tradeoffs are discussed. We have used one of our schemes to replace the current BSD UNIX callout and timer facilities. Our new implementation can support thousands of outstanding timers without much overhead. Our timer schemes have also been implemented in other operating systems and network protocol packages     

Digital Carrier Modulation and Sampling Issues of Matrix Converters

Although the modulation of ac–ac matrix converters using space vector theory has long been established, their carrier-based modulation principles have only recently attracted some attention. Reasons commonly stated for evaluating the carrier-based alternative include simpler converter control because of its inherent autosequencing process, and easier implementation using fast on-chip timers embedded in most modern digital signal processors. Motivated by these likely merits, which have previously been proven for dc–ac inverters, an investigation is now pursued here to develop appropriate digital carrier modulation schemes for controlling conventional (direct) and indirect matrix converters with minimized semiconductor commutation count and smooth sextant transitions with no erroneous states produced. For guaranteeing the latter two features, correct digital sampling instants and state sequence reversal must be chosen appropriately, as demonstrated in the paper for the two different topological options, which, to date, have not yet been discussed in the existing literature. To validate the concepts discussed, experimental testing on the implemented conventional and indirect matrix laboratory prototypes was performed with their respective results captured and presented in the paper for visual confirmation.      

通信软件中定时器库的设计与实现

阐述了在通信软件中定时器库的需求以及现有定时器的缺陷，运用C＋＋高级编程技术STL和BOOST库，对系统底层的定时器库进行了设计与实现。     

USB外设计时控制器的设计

描述了-套基于单片机,能实现对电脑USB外围设备进行计时控制,同时兼具实时时钟显示功能的电路系统设计.很好地解决了长期困扰电脑使用者不能计时控制USB外设的难题.根据89S52单片机所具有的三路独立定时器资源,本设计对USB定时控制功能和计时功能进行了合理规划,相对于其它同类的设计仅束缚于两路定时器甚至一路有了很大的提高.本论文从设计方案、软硬件设计实现等多方面对设计进行了详细的阐述.实验结果证实本设计能满足各项设计功能并达到很好的效果.     

Speed measurement using the improved DMA transfer method

A wide-range speed measurement method using the direct memory access (DMA) transfer of a content of the timer to the memory is presented. The DMA method is based on both pulse counting and time measurement during the constant sampling time. The hardware configuration and algorithms for a microcontroller implementation are also presented. The proposed method is suitable in systems using microcontrollers with integrated DMA controller and timers. Limitations and sources of errors are discussed in detail     

On the use of the IEEE 802.4 token bus in distributed real-timecontrol systems

The performance of the IEEE 802.4 priority mechanism in handling distributed real-time control traffic is examined. A timer assignment technique is presented for such applications. The timers are set to satisfy the worst-case access delay requirements of real-time control applications. Other applications that are not time constrained can be supported simultaneously. Under certain conditions, such applications can also be guaranteed a minimum bandwidth allocation. Simulation results are used to evaluate the timer assignment scheme     

Windows环境下多串口控制软件设计中精确定时的实现

在模拟飞控软件设计中,需要通过实现串口通信的精确定时来测试系统的实时性能。本文分析对比了Windows环境下VC++软件多种定时器的性能,并在模拟飞行控制软件中进行了测试比较。测试结果表明:在Windows环境下采用软件定时器,其性能难以满足高精度定时需求。为此,本文提出了一种硬件同步与软件定时相结合的精确定时方式,可将串口通信的定时精度提高到微秒量级。     

Determination of LTPB parameters to guarantee message deadlines

A bandwidth allocation scheme for a linear token passing multiplex data bus is proposed based on balancing message transmission time with traffic load to each node. It is proved to provide a network worst case achievable utilization of 50%. Under this allocation scheme, closed-form expressions for the initialized value of token holding timers and token rotation timers in each node are obtained.     

玫瑰扫描系统中提取目标方位信息的方法

在分析了几种玫瑰扫描系统中目标方位信息提取方法的基础上,提出一种简单有效的方位信息提取方法。这种方法是根据,玫瑰扫描系统中两反射镜绕轴转过的角度唯于决定瞬时视场的位置,当目标脉冲到来时记下两反射镜绕轴转过的角度,就可以确定此时的目标位置,从而找到了确定目标方位信息的关键,彻底解决了初相位问题。在两个反射上安装光电探测器,使之转一周产生一个脉冲信号作为基准信号。用两个计时器,分别对应于两个反射镜,当     

基于定时器超时时刻调整的低功耗技术

针对通信系统中各定时器和网络端时钟频繁产生中断使系统过早进入工作状态的问题,结合移动终端的特点,提出一种基于定时器超时时刻调整的低功耗技术,并且从理论和实践上进行验证,该技术能够使设备尽可能地处于睡眠状态,有效地降低了系统功耗,对推动移动通信产业的发展具有重大意义。     

基于多尺度分解的k邻域随机查找快速图像修复

该文提出一种基于多尺度分解的k邻域随机查找快速图像修复方法。基于双边滤波下采样分解图像,从图像最粗糙层开始,对每一粗糙层采用基于最小堆的k邻域随机查找算法快速搜索最佳匹配块,利用鲁棒优先级函数确定下一待修复块。每一粗糙层修复后用双边滤波上采样重建下一粗糙层,迭代得到最终的修复结果。与相关工作比较,所提方法的修复结果能够保持图像的细节和边缘信息,取得更高的修复质量。利用客观指标评价修复结果。实验结果表明该方法有效易行,修复的图像具有良好的可视效果。     

Special Purpose Timer to Aid in Closed Circuit Anesthesia Delivery

Closed circuit anesthesia systems offer certain advantages over other techniques, but require that gas administration closely foliow the uptake by the body, which is proportional to the square root of time. We have developed a timer which automatically signals the anesthesiologist to readjust the gas flow at selected intervals to provide a stepwise approximation to the square root of time curve. Two additional nonsignaling timers are included to permit timing of total elapsed anesthesia time and a third event.     

Frequency estimator with dichotomous search of periodogram peak

A new simple frequency estimator is presented which performs FFT-based coarse and DFT-based dichotomous fine searching of the periodogram peak. The proposed estimator is shown to have a frequency error close to that of the maximum likelihood (ML) estimator and a lower complexity than that of known estimators     

带延时功能的微波自动报警系统的设计

设计了一个由微波发射器、555定时器、电压比较器和继电器组成的具有延时功能的自动报警器。该报警器由微波探头检测活动物体,将波动的电磁场信号转化为波动的电压信号后输出给电压比较器,电压比较器比较后的高电平触发555定时器工作,经过延时后的信号触发继电器报警。该报警系统克服了一般报警器容易出现的漏报警现象和其他微波报警器容易受外界电磁场的干扰所引起的误报警的缺点,很好地解决了报警系统的灵敏性与可靠性之间的矛盾。     

m-DIBCR: MAC Protocol with Multiple-Step Distributed In-Band Channel Reservation

A new medium access control (MAC) protocol to handle packet collisions is proposed. Different from traditional MAC protocols, where only one-step reservation is considered, we propose a multiple-step distributed in-band channel reservation, called m-DIBCR, where m represents the number of steps we consider in the channel reservation. In the protocol, each node maintains m timers, each of which serves as the backoff timer for one of the next m packets to be sent. A node broadcasts the initial values of these timers by piggybacking them in the data packet, and simultaneous transmissions can be avoided when its neighboring nodes overhear these values. Extensive simulations show that, compared with one-step channel reservation, throughput can be dramatically improved by multiple-step channel reservation, especially in networks with high transmission error probabilities and/or a large number of contending nodes.     

一种由粗到精的快速车牌定位算法

提出一种由粗到精的分步快速车牌定位算法.它首先运用数学形态学线形算子增强车牌等水平边缘密集区域得到粗定位车牌;对粗定位候选车牌区进行二值化,利用线扫描等特征获取车牌精确定位.大量测试实验结果表明,该定位算法快速、准确.     

cdma2000 1x EV-DO的掉话原理分析及解决思路

本文结合cdma2000 1x EV-DO的技术特点阐述了EV-DO系统中造成掉话的几种情况,重点涉及EV-DO前向和反向掉话机制以及优化方法,和传统的cdma2000 1x掉话做了对比,另外还介绍了影响掉话指标的几个关键定时器。     

Digital Coarse Tuning Loop for Wide-Band Fast-Settling Dual-Loop Frequency Synthesizers

提出了一种用于宽带、双环路频率综合器的粗调环路结构.该粗调环路由数字电路设计实现,包含逐次逼近寄存器和新结构的频率比较单元两个模块.其中,频率比较单元在一定的参考时间内对预分频器的输出信号周期进行计数,然后通过比较计数结果与预设值的大小来估计VCO输出频率.对比较误差进行了详细分析,分析表明,在一定的比较时间内该结构的比较误差比现有结构小20倍,而且由于重复利用可编程分频器作为粗调环路的一部分,整体电路也大为简化.     

快速锁定、宽带双环路频率综合器的数字粗调环路

提出了一种用于宽带、双环路频率综合器的粗调环路结构.该粗调环路由数字电路设计实现,包含逐次逼近寄存器和新结构的频率比较单元两个模块.其中,频率比较单元在一定的参考时间内对预分频器的输出信号周期进行计数,然后通过比较计数结果与预设值的大小来估计VCO输出频率.对比较误差进行了详细分析,分析表明,在一定的比较时间内该结构的比较误差比现有结构小20倍,而且由于重复利用可编程分频器作为粗调环路的一部分,整体电路也大为简化.     

改进的隐式空间映射算法的研究

介绍了一种快速收敛空间映射算法,改进了隐式空间映射算法中粗糙模型到精细模型之间参数映射。通过增加限定参数提取的方式,减少粗糙模型的参数空间而实现粗糙模型响应高效准确逼近精细模型响应。通过设计一个交叉耦合滤波器,与之前的隐式空间算法进行比较,更容易达到优化目标,证明了限定参数提取算法具有更快的逼近速度和更高的优化效率的优点。