In this dissertation, the authors studied and analyzed an algorithm predicting the execution time of task by the linear relationship between host load and the execution time of task. 结合主机负载和任务执行时间的线性关系,研究分析了一种基于主机负载的任务执行时间预测算法。
The simulation results show that MCUD algorithm further decreases the total execution cost and total execution time while meeting the user-designated deadline in comparison with other algorithms. 仿真实验表明,MCUD相比于其他算法,在满足总的最后期限的前提下更进一步地降低了执行成本和执行时间。
The result shows that the algorithm can produce a satisfied execution plan in less time. 结果显示,算法能在较短的时间内产生令人满意的执行计划。
Then the mechanism of Simulated Annealing is import in the algorithm above to decrease the execution time and quickens the velocity of convergence. 然后,为了加快遗传算法的收敛速度减少算法执行时间引入模拟退火机制对上述算法进行优化。
Simulation results show that the retrieval algorithm under the new organization of the inverted file can decrease its execution time significantly, and the optimal parameter selection for this blocking organization is discussed. 通过建立检索性能模型,进行分析和仿真实验,结果表明这一方法下的检索算法可以有效的减少检索执行时间,并得到这一组织方式中分块参数的优化选择方法。
On the basis of analyzing the recent schedule algorithm, we find that recent work mainly focuses on how to optimize task schedule to minimize the execution time of the whole workflow, ignoring malfunction of grid resource. 在分析了目前的调度算法的基础上,我们发现目前的主要工作是集中在如何优化任务的调度来最小化整个工作流的执行时间,忽视了网格资源失效以及失效对网格应用程序的影响。
This paper introduces an effective scheduling algorithm in UET ( Unit Execution Time) system, its time complexity function being O ( na ( n)+ e). 本文介绍了一种UET系统中有效的调度算法,其时间复杂性函数为O(na(n)+e)。
The algorithm improves cache hit rate by transposing the matrix and consequently reduces the execution time of the matrix multiplication. 该算法转置矩阵,提高cache命中率,从而降低矩阵乘积时间。
Fault-tolerant real-time scheduling algorithm based on the time redundancy, whose schedulability bound is based on the worst execution time of tasks and the time reserved for tasks 'fault-tolerant operation, has a high rejection rate and low resource utilization. 基于时间冗余的实时容错调度算法,可调度条件以任务的最坏执行时间和为任务预留容错操作的时间为分析基础,任务拒绝率高,系统资源利用率低。
The parameter identification method and dynamic hierarchical control theory are used to investigate the trajectory control of robotic manipulators. A multi-microprocessor-based adaptive control algorithm of high path tracking precision, short execution time and easy implementation is proposed. 本文应用参数辨识和动态递阶控制方法研究工业机器人轨迹控制问题,提出了一种采用多微机系统的自适应控制算法,其在线执行时间短,便于实现。
The heuristic algorithm is the gain of the execution time. The partitioning model is constructed and the result is searched. 给出了系统划分模型,使用执行时间最少的增益函数启发下一步动作的启发算法。
Experimental results also show that the new algorithm 2 is faster than new algorithm 1 because of the lower execution time on creating subsets. 且新算法2由于创建数据库子集的时间开销比新算法1小,因而比新算法1的运行速度更快,所以新算法2比新算法1更适于挖掘大型数据库。
The proposed algorithm gains better candidate generation quality by introducing a new Lemma to help to target the combinations of episodes that are interesting in the next level and thus reduces the execution time. 该算法通过一个新的引理,帮助进一步确定下一级中感兴趣的情节组合,从而获得了较高质量的候选集,缩短了执行时间。
Motivated by this observation, this paper proposes a hybrid evolutionary algorithm that can be used to enable a flexible tradeoff between the code size and execution time of a program by using the two instruction sets selectively for different parts of a program. 针对这种现象,文中建议一个混合演化算法,通过把程序的不同部分有选择地编译成ARM或Thumb指令集代码,使得可灵活地权衡目标代码大小和运行时间。
Simulation results show that the schedule length of the proposed algorithm is on the average 14.7% better than that of the genetic algorithms, but its execution time is almost half of the latter. thus it is especially suitable to the large scale task scheduling. 仿真实验结果表明,与遗传算法相比,调度长度提高14.7%,运行时间缩短近一半,特别适合于求解规模较大的多处理器任务调度问题。
Experimental results show that the increment based on artificial immune clustering algorithm error and the average classes in terms of algorithm execution time are reflected in good performance. 经过实验验证,基于人工免疫增量的聚类算法在平均类内误差和算法执行时间等方面均体现出良好的性能。
At the same time, the algorithm can effectively reduce execution time and execution cost of instance-intensive workflow in the cloud computing environment. 同时,该算法还可以有效地降低云计算环境下实例密集型工作流实例的执行时间和执行成本。
Compare with the FCFS algorithm and the backfill algorithm with no prediction execution time parameter, the load of the system resources can reach the better performance by the backfill algorithm with the prediction execution time parameter. 相比于FCFS算法和无预测时间参数的回填算法,有预测时间参数的回填算法可获得更好的资源负载性能。
Therefore, it is necessary to use other computing devices to reduce the audio retrieval algorithm execution time. 因此,有必要利用其它计算设备加速音频检索算法。
Simulation results show that the algorithm can well meet the need of using data center under cloud environment, improve load balancing degree of resources and curtail the relative execution time. 模拟实验结果表明,该算法能很好的满足云环境下数据中心的使用要求,提高资源的负载均衡度,减少任务的相对执行时间。
The ability evaluation index and the improved ant colony algorithm can not only help to obtain the parameters that are difficult to be estimated, such as the workflow execution time, but also make the task scheduling algorithm more dynamical and adaptive. 3. 实验结果表明,改进的蚁群任务调度算法,不但能够解决工作流执行时间等参数难于估算的问题,而且能提高任务调度的动态适应性。3、基于数据划分的任务分解与调度算法。
In the prediction execution time algorithm, we adopt multiple linear regressions modeling to obtain the most similar task execution time and then correct the execution time by dynamic resources factors. 在执行时间预测算法中,采用多元线性回归模型建模,比较出最相似任务的执行时间并且根据各个资源因素的动态性进行了相关矫正。
However, in such an application scenario, a longer algorithm ( protocol) execution time in exchange for the distributed implementation is entirely desirable. 不过在这样一种应用场景下,以更长的算法(协议)执行时间为代价换取分布式实现的方案是完全可取的。
The results showed that, compared with the image matching algorithm, the algorithm reduces the execution time by about 80%. 4. 实验表明,该算法与已有的图像特征点匹配算法相比,执行时间缩短了约80%。
The main idea of the algorithm is by copying the tasks which are not assigned to the same node with their successors. By this way we can shorten the task execution time and reduce the communication energy consumption. 算法的主要思想是通过复制任务,使任务的副本分配到与其不在同一节点执行的后继任务之前,通过这种方式缩短任务的执行时间并且减少通信的能耗。
The algorithm considers the trust of users 'task needs, to achieve resources load balancing, and takes into account the task execution time span, the average waiting time and other factors. 该算法考虑了用户任务的信任需求,以资源负载均衡为目标,同时兼顾任务执行时间跨度,任务平均等待时间等因素。
Although the standard fuzzy C-means clustering segmentation algorithm fully take into account the character of image, it is just good at to segment the image that is in normal distribution or ball distribution and its execution time is very long. 标准的模糊C均值聚类分割算法充分考虑到了图像的特征,但却仅对类似于正态分布或球类分布的图像具有较好的分割效果,且算法执行时间较长。