可变压处理器上硬实时系统的作业调度

在设计实时嵌入式系统时，如果能够善于利用可变电压处理器。可以极大减少系统的能耗。介绍了在动态优先级和静态优先级情况下，确定调度某个给定作业集所需最低电压常量，确定可变电压处理器的最优电压调度方案的思想和算法。     

一种基于优先级队列的集群动态反馈调度算法

在分析现有面向LVS集群的负载均衡调度算法优缺点的基础上,提出了一种新的调度算法—基于优先级队列的动态反馈调度算法。该算法根据定期采集到的各服务器负载信息动态地调整各服务器的权值,并根据权值建立优先级调度队列借以实现连接的调度。算法可保证良好的负载均衡性,且时间复杂度降低至O(1)。     

Web服务调度策略的研究

Web服务调度是Web服务组合中的一个重要环节,直接影响着服务组合的效率。文章研究了目前Web服务器广泛使用的调度策略:先来先服务策略(FCFS),优先级策略(Priority),分析了其优缺点。在此基础上,结合静态和动态两方面因素,提出了基于服务器负载的优先级调度策略,其中优先级的设定通过将服务费用同执行时间相绑定。文章最后设计了该调度策略的算法,通过实验将它和优先级策略进行了比较。摘要     

综合优先级下相控阵火控雷达自适应调度算法

针对相控阵火控雷达多任务调度时的资源分配问题，提出一种综合优先级下的自适应调度算法。基于相控阵火控雷达需与高炮配合对待拦截目标进行火力打击的特性，进行目标射击有利度求解。利用两级二维优先级表级联的思想，结合目标射击有利度、工作方式优先级和任务截止期进行综合优先级规划。以加权时间偏移量平方和最小作为调度代价准则，构建任务调度代价模型，提出带有时间窗的一步回溯法与插空法相结合的自适应调度算法，并利用该算法求解调度模型。通过仿真将本文所提调度算法与传统工作方式优先级加截止期调度算法进行对比分析，结果表明：相比传统调度算法，本文所提调度算法提升了射击价值率，降低了平均时间偏移率和调度代价。     

基于非线性因子的改进鸟群算法在动态能耗管理中的应用

针对实时系统能耗管理中动态电压调节(DVS)技术的应用会导致系统可靠性下降的问题,该文提出一种基于改进鸟群(IoBSA)算法的动态能耗管理法。首先,采用佳点集原理均匀地初始化种群,从而提高初始解的质量,有效增强种群多样性;其次,为了更好地平衡BSA算法的全局和局部搜索能力,提出非线性动态调整因子;接着,针对嵌入式实时系统中处理器频率可以动态调整的特点,建立具有时间和可靠性约束的功耗模型;最后,在保证实时性和稳定性的前提下,利用提出的IoBSA算法,寻求最小能耗的解决方案。通过实验结果表明,与传统BSA等常见算法相比,改进鸟群算法在求解最小能耗上有着很强的优势及较快的处理速度。     

基于无线传感器网络能耗系统的研究

节能已经成为无线传感器网络研究的核心部分。该文研究了无线传感器网络拓扑结构的邻近节点数对网络能耗的影响,主要采用动态电压调节技术(DVS)来降低无线传感器网络中节点的能耗。动态电压调节主要通过减少门等效电容、供电电压以及降低转换因子、时钟频率来达到降低动态能耗的目的,其中,降低供电电压节能效果最佳。与其他方法相比,动态电压调节降低能耗更加明显、效率更高。通过在CC2430节点芯片上测试验证,通过改变其分频比,得出了功耗和频率的近似线性关系。     

处理器可靠性约束的电压频率岛NoC能耗优化

该文针对支持电压频率岛的NoC能耗优化问题,提出了基于电压频率岛划分、分配以及任务映射的能耗优化方法。该方法通过基于处理器可靠性约束的电压频率岛划分,降低了处理器能耗;利用近凸区域选择的电压频率岛分配策略,减少了不同电压岛间复杂路由器的个数;借助量子粒子群算法优化了NoC映射,降低了系统的通信能耗。实验结果表明,该文算法在满足NoC处理器可靠性要求的前提下,可显著降低NoC系统能耗。     

传感器网络的任务双效节能调度研究

能源供应有限性是局限传感器网络的性能和存活寿命的重要因素,本文从传感器网络节点的任务调度出发,提出动态能量管理DPM和动态电压/频率调节DV/FS的双效处理器节能调度算法,即DV/FS-RM和DV/FS-EDF调度算法;在DPM动态控制空闲任务进入休眠的同时,在保证节点的实时性的前提下,通过DV/FS-RM或DV/FS-EDF算法降低处理器频率,达到更好的节能效果.实验显示,该节能任务调度算法使以电池为能源的传感器网络节点的生存期成倍地延长.     

基于概率性分析的混合关键级系统节能调度算法

针对混合关键级系统中的固定优先级任务节能问题,文中提出了基于概率性分析的混合关键级系统节能调度算法。混合关键级系统的实时性要求使得系统建模和分析偏向于较坏的情况。该类系统中出现任务超限的情况相对较少,易存在资源配置过度问题。通过DVFS(Dynamic Voltage Frequency Scaling)技术和混合关键级系统调度算法相结合的方式挖掘空闲时间,从而在保证系统实时性的前提下降低系统的能耗。利用MCSIMU仿真软件对所提算法进行了仿真验证,实验结果表明,对于固定优先级任务与未使用节能调度算法相比,固定优先级节能调度算法的节能率可达45%。     

硬实时系统中基于任务同步及节能的动态调度算法

提出基于任务同步及节能的动态实时调度算法HDSA(hybrid dynamic scheduling algorithm),以有效地解决任务同步及节能的难题.HDSA 结合RM及EDF算法,在满足任务实时可调度性及任务同步的限制条件下,采用DVFS节省能耗.HDSA包含静态算法及动态算法两部分.静态算法在静态条件下,求出任务的静态速度.动态调度算法在实际运行中,固定临界区的运行速度,并充分回收、利用任务运行时的空闲执行时间,调节处理器的速度,以有效降低能耗并满足实时可调度性.同时避免高优先权任务被阻塞时,临界区继承高优先权任务的速度时所造成的处理器电压开关的频繁切换,因而能有效地降低实时任务调度的成本.实验测试表明,HDSA在调度性能上明显优于目前所知的有效算法.     

Energy-efficient scheduling for multiprocessors

An energy-efficient scheduling algorithm is proposed for parallel tasks in a multiprocessor system. The proposed algorithm utilises the dynamic voltage scaling (DVS) method for low energy consumption and executes tasks in parallel to compensate for the execution delay induced by the DVS method     

动态电压调整多处理器实时系统任务调度

动态电压调整DVS（Dynamic Voltage Scaling）是根据处理器电压（速度）降低之后，能量消耗平方级的减少这一原理提出的。文章通过DVS机制在多处理器实时系统中进行任务调度．通过对任务调度中的静态能量管理进行分析，在此基础上提出了一种新的基于DVS的适用于多处理器实时系统中的调度算法。这种新的调度算法是通过对贪婪法调度进行研究，发现其不足．并以此为基础进行改进。结合了动态电压调整的多处理器实时系统任务调度的能量消耗比普通的任务调度能量消耗有了很大的改善。     

Multidimensional QoS cloud computing resource scheduling method based on stakeholder perspective

A multidimensional cloud computing architecture is designed and a multidimensional cloud resource scheduling model is constructed based on the stakeholder perspective of cloud users and cloud service providers to meet the high QoS requirements of cloud users (such as task execution time and task completion time) with low computing costs (such as energy consumption,economic costs and system availability).For the second-level cloud resource scheduling,an MQoS cloud resource scheduling algorithm based on multiple Greedy algorithm is proposed.The experimental results show that under the four cloud computing application scenarios with no aftereffects,the MQoS cloud resource scheduling algorithm has an overall increase of 206.42%~228.99% and 34.26%~56.93 in terms of multidimensional QoS degree compared with FIFO and M2EC algorithms.It has an average overall reduction of 0.48~0.49 and 0.20~0.27 in terms of cloud data center load balance difference.     

Elastic DVS Management in Processors With Discrete Voltage/Frequency Modes

Applying classical dynamic voltage scaling (DVS) techniques to real-time systems running on processors with discrete voltage/frequency modes causes a waste of computational resources. In fact, whenever the ideal speed level computed by the DVS algorithm is not available in the system, to guarantee the feasibility of the task set, the processor speed must be set to the nearest level greater than the optimal one, thus underutilizing the system. Whenever the task set allows a certain degree of flexibility in specifying timing constraints, rate adaptation techniques can be adopted to balance performance (which is a function of task rates) versus energy consumption (which is a function of the processor speed). In this paper, we propose a new method that combines discrete DVS management with elastic scheduling to fully exploit the available computational resources. Depending on the application requirements, the algorithm can be set to improve performance or reduce energy consumption, so enhancing the flexibility of the system. A reclaiming mechanism is also used to take advantage of early completions. To make the proposed approach usable in real-world applications, the task model is enhanced to consider some of the real CPU characteristics, such as discrete voltage/frequency levels, switching overhead, task execution times nonlinear with the frequency, and tasks with different power consumption. Implementation issues and experimental results for the proposed algorithm are also discussed     

面向拟态云服务的异构执行体调度算法

针对当前异构调度模型仅从空间或者时间特性进行建模设计,缺少对时空特性的综合考虑且存在动态性和异构性不够均衡的问题。为使拟态云服务系统的动态、异构和冗余特性能够平衡互补,提出一种基于优先级和时间片的执行池调度算法,该算法基于执行池相似性指标进行优先级预排序,结合时间片等策略进行方案调度。实验结果表明,所提算法有较好的动态性,结合时间片策略能够获得动态性和异构性的综合平衡,且算法耗时较低。     

面向密集多波束组网的卫星通信系统资源调度算法

研究了高动态、资源受限条件下的卫星通信系统资源调度问题.以时间窗口、卫星功耗、信道数量、用户优先级以及任务突发性为约束,建立了卫星资源调度模型.考虑到传统的蚁群优化算法存在初期搜索速度过慢、局部搜索能力较弱以及易陷入局部最优等缺点,提出了以初始解集构造、额外信息素沉积为核心的改进蚁群优化算法,来求解资源调度问题.仿真实...     

Energy-Optimal Uplink Scheduling in Mobile Cloud Systems

This paper investigates the energy-optimal uplink scheduling in mobile cloud systems. We establish a framework to optimize the energy consumption of the terminal using OFDM technology. We first consider the fixed overhead of RRC state promotion, then, we optimize the energy consumption in slow-start stage and normal transmission stage respectively. In normal data transmission stage, we consider both single-channel transmission scenario and multi-channel transmission scenario. In single-channel transmission scenario, we present an uplink scheduling algorithm which uses dynamic programming method to adjust the transmission rate in accordance with the fluctuating multi-states channel gain. In multi-channel transmission scenario, we propose four different algorithms respectively. Two algorithms of them allocate the transmission rate only among sub-channels and the other two allocate the transmission rate among both time slots and sub-channels. The numerical results show that when the average transmission rate is low, significant amount of energy can be saved by the presented algorithms. The results provide a method for mobile terminals to save energy, i.e., uploading applications to the cloud when data size is small or when the terminal is allocated with wide spectral bandwidth.     

Research on optimal two element exchange algorithm for large scale cloud computing server scheduling problem

With the flourishing of cloud computing industry,the rational management and scientific scheduling of cloud computing servers has become an important issue.In terms of model,a new mixed integer programming (MIP) model with affinity constraints and anti-affinity constraints was proposed to describe the scheduling problem of large scale cloud computing server.Considering the time cost of solving large-scale MIP problems,an optimal two element exchange algorithm was designed with the basics of branch and bound method and local search algorithm.By constantly extracting MIP sub-problems from completing scheduling problems and using branch and bound method to solve the sub-problems,the algorithm continuously optimized the server scheduling schemes,so that the scheduling schemes approached the optimal solution.The experimental results show that the algorithm has great advantages over the other methods in testing data set ALISS,and can reduce the resource consumption of cloud computing center by more than 4% when the same task is completed.     

Simultaneous Dynamic Voltage Scaling of Processors and Communication Links in Real-Time Distributed Embedded Systems

Dynamic voltage scaling has been widely acknowledged as a powerful technique for trading off power consumption and delay for processors. Recently, variable-frequency (and variable-voltage) parallel and serial links have also been proposed, which can save link power consumption by exploiting variations in the bandwidth requirement. This provides a new dimension for power optimization in a distributed embedded system connected by a voltage-scalable interconnection network. At the same time, it imposes new challenges for variable-voltage scheduling as well as flow control. First, the variable-voltage scheduling algorithm should be able to trade off the power consumption and delay jointly for both processors and links. Second, for the variable-frequency network, the scheduling algorithm should not only consider the real-time constraints, but should also be consistent with the underlying flow control techniques. In this paper, we address joint dynamic voltage scaling for variable-voltage processors and communication links in such systems. We propose a scheduling algorithm for real-time applications that captures both data flow and control flow information. It performs efficient routing of communication events through multihops, as well as efficient slack allocation among heterogeneous processors and communication links to maximize energy savings, while meeting all real-time constraints. Our experimental study shows that on an average, joint voltage scaling on processors and links can achieve 32% less power compared with voltage scaling on processors alone