云计算中Hadoop平台上默认调度方式FIFO是以公平性为目标,然而考虑单一因素会使资源利用率低下以及任务完成时间过长。在公平性和完成时间的权衡中,运行时间指标更为重要。据此,建立云计算下多资源和应用程序任务以及调度的数学模型和...云计算中Hadoop平台上默认调度方式FIFO是以公平性为目标,然而考虑单一因素会使资源利用率低下以及任务完成时间过长。在公平性和完成时间的权衡中,运行时间指标更为重要。据此,建立云计算下多资源和应用程序任务以及调度的数学模型和其目标函数,运用归约方法和具有强大计算能力的工具MINI SAT SOLVER去求解问题。仿真实验结果表明,在不同的资源供给条件下,基于MINI SAT SOLVER的次优算法比YARN(Yet Another Resource Negotiator)中默认的调度算法FIFO缩短了任务的完工时间,优化比率最高可以达到30%。展开更多
One way of increasing the computational speed is by using multiple computers operating together on a sin-gle problem. The overall problem is split into parts, each of which is performed by a separate processor in para...One way of increasing the computational speed is by using multiple computers operating together on a sin-gle problem. The overall problem is split into parts, each of which is performed by a separate processor in parallel.Writing programs for this form of computation is known as parallel programming. Equipped by electrical power moni-toring system of Shanghai Hongqiao international airport, this report clarifies the methods of parallel processing.展开更多
为解决橡胶轮胎硫化过程耗时长,能源消耗大,集中度较高的问题,提出了一种离散的分布估计算法(Estimation of Distribution Algorithm,EDA)来求解以最小化最大完工时间为优化目标的硫化车间调度优化问题。通过不同的算例来测试该算法的性...为解决橡胶轮胎硫化过程耗时长,能源消耗大,集中度较高的问题,提出了一种离散的分布估计算法(Estimation of Distribution Algorithm,EDA)来求解以最小化最大完工时间为优化目标的硫化车间调度优化问题。通过不同的算例来测试该算法的性能,并与遗传算法和和声搜索算法进行实验比较。实验结果表明,EDA算法在优化解的质量和收敛速度方面都要优于遗传算法和和声搜索算法,验证了该算法在求解硫化车间调度优化问题中的有效性和可行性。展开更多
文摘云计算中Hadoop平台上默认调度方式FIFO是以公平性为目标,然而考虑单一因素会使资源利用率低下以及任务完成时间过长。在公平性和完成时间的权衡中,运行时间指标更为重要。据此,建立云计算下多资源和应用程序任务以及调度的数学模型和其目标函数,运用归约方法和具有强大计算能力的工具MINI SAT SOLVER去求解问题。仿真实验结果表明,在不同的资源供给条件下,基于MINI SAT SOLVER的次优算法比YARN(Yet Another Resource Negotiator)中默认的调度算法FIFO缩短了任务的完工时间,优化比率最高可以达到30%。
文摘One way of increasing the computational speed is by using multiple computers operating together on a sin-gle problem. The overall problem is split into parts, each of which is performed by a separate processor in parallel.Writing programs for this form of computation is known as parallel programming. Equipped by electrical power moni-toring system of Shanghai Hongqiao international airport, this report clarifies the methods of parallel processing.
文摘为解决橡胶轮胎硫化过程耗时长,能源消耗大,集中度较高的问题,提出了一种离散的分布估计算法(Estimation of Distribution Algorithm,EDA)来求解以最小化最大完工时间为优化目标的硫化车间调度优化问题。通过不同的算例来测试该算法的性能,并与遗传算法和和声搜索算法进行实验比较。实验结果表明,EDA算法在优化解的质量和收敛速度方面都要优于遗传算法和和声搜索算法,验证了该算法在求解硫化车间调度优化问题中的有效性和可行性。
