嵌入式系统动态电源管理预测算法研究

针对目前在嵌入式系统中动态电源管理普遍采用超时算法节能效率低的缺点,采用预测的方法进行动态电源管理。提出一个动态电源管理预测算法,该算法通过利用设备空闲状态的历史信息对未来的空闲时间进行预测,预测结果作为动态电源管理的依据。实验结果说明该算法对工作状态平稳的系统空闲预测效果比较理想,适用于动态电源管理。

一种基于活跃态的动态电源管理预测算法

提出一种基于活跃态的动态电源管理预测算法,充分利用了活跃态和空闲时间段的关系,并且加入动态自适应调节因子,不仅对较大变化的时间段预测误差小,而且能快速调整适应工作负载的变化。实验表明该算法优于传统算法。

网络时间同步算法及其实现

随着计算机网络越来越广泛的应用,网络时间同步的要求也越来越重要。本文介绍了网络时间同步的有关概念,讨论了实现网络时间同步的一般方案,详细分析了我们提出的网络时间同步算法——超时算法,并给出了实现结果。

星空运动小目标轨迹检测超时控制

针对天基观测星图的特点,分析了星空背景下运动小目标检测算法超时和虚警率过高的原因,引入并改进了MTI滤波器对序列星图进行处理,避免了恒星识别的繁重计算;改进了小目标关联算法结构,在精确度较高的情况下较大范围地提高了算法效率。实验结果表明,改进算法耗时大大减少,能够有效控制算法超时和虚警率过高的风险,满足天基观测星图运动小目标轨迹检测的工程实际需要。

FPGA-based High-precision Measurement Algorithm for the Ultrasonic Echo Time of Flight

Based on the evaluation of advantages and disadvantages of high-precision digital time interval measuring algorithms, and combined with the principle of the typical time-difference ultrasonic flow measurement, the requirements for the measurement of echo time of flight put forward by the ultrasonic flow measurement are analyzed. A new high-precision time interval measurement algorithm is presented, which combines the pulse counting method with the phase delay interpolation. The pulse counting method is used to ensure a large dynamic measuring range, and a double-edge triggering counter is designed to improve the accuracy and reduce the counting quantization error. The phase delay interpolation is used to reduce the quantization error of pulse counting for further improving the time measurement resolution. Test data show that the systexn for the measurement of the ultrasonic echo time of flight based on this algorithm and implemented on an Field Programmable Gate Army（FleA） needs a relatively short time for measurement, and has a measurement error of less than 105 ps.