Exascale computing is one of the major challenges of this decade,and several studies have shown that communications are becoming one of the bottlenecks for scaling parallel applications.The analysis on the characteris...Exascale computing is one of the major challenges of this decade,and several studies have shown that communications are becoming one of the bottlenecks for scaling parallel applications.The analysis on the characteristics of communications can effectively aid to improve the performance of scientific applications.In this paper,we focus on the statistical regularity in time-dimension communication characteristics for representative scientific applications on supercomputer systems,and then prove that the distribution of communication-event intervals has a power-law decay,which is common in scientific interests and human activities.We verify the distribution of communication-event intervals has really a power-law decay on the Tianhe-2 supercomputer,and also on the other six parallel systems with three different network topologies and two routing policies.In order to do a quantitative study on the power-law distribution,we exploit two groups of statistics:bursty vs.memory and periodicity vs.dispersion.Our results indicate that the communication events show a“strong-bursty and weak-memory”characteristic and the communication event intervals show the periodicity and the dispersion.Finally,our research provides an insight into the relationship between communication optimizations and time-dimension communication characteristics.展开更多
针对时变速度下的低碳配送需求,本文以配送总成本最小化为目标,构建考虑三维装载和时间窗约束的绿色车辆路径优化模型。模型考虑时变速度和实时载重对车辆燃油消耗量的影响。为准确计算行驶时间和油耗,采用二分K-means聚类算法对时段进...针对时变速度下的低碳配送需求,本文以配送总成本最小化为目标,构建考虑三维装载和时间窗约束的绿色车辆路径优化模型。模型考虑时变速度和实时载重对车辆燃油消耗量的影响。为准确计算行驶时间和油耗,采用二分K-means聚类算法对时段进行合理划分。设计两阶段算法求解模型:第一阶段采用自适应大规模邻域搜索(adaptive large neighborhood search,ALNS)算法以确定车辆配送路径;第二阶段采用遗传算法(genetic algorithm,GA)对货物进行三维装载顺序的可行性校验。算例结果表明,基于二分K-means聚类算法的时段划分方法能更精确地计算总成本,从而验证了本文所构建的模型和所设计的算法具有可行性和有效性。展开更多
山东省是畜牧业大省,猪肉价格波动对居民生活质量有着重大影响,目前,关于山东省生猪价格波动的预测研究较少,且存在预测时间较短,时间窗口狭窄和预测结果不准确等问题。针对传统预测模型存在长时序预测准确率不足的问题,本文提出了一种...山东省是畜牧业大省,猪肉价格波动对居民生活质量有着重大影响,目前,关于山东省生猪价格波动的预测研究较少,且存在预测时间较短,时间窗口狭窄和预测结果不准确等问题。针对传统预测模型存在长时序预测准确率不足的问题,本文提出了一种基于综合决策机制的时间序列预测模型。首先,将时间序列信息进行分解,通过可逆归一化将数据特征进行放大,以提取更多的价格波动信息;在信息分解的基础上,通过上采样扩充先验知识,并采用多维度综合决策的方式,增强多层感知机的数据特征挖掘能力和决策能力;最后,将先验知识与预测结果进行直接映射,解决了窗口狭窄和滑动窗口迭代预测导致的误差累积问题。试验结果表明,相较于ARIMA、Prophet-BP、GA-BP、VMD-LSTM和STL-Informer模型,本文算法在RMSE(Root mean square error)和MAE(Mean absolute error)指标上平均提升了50.2%和30.9%,在R^(2)(Coefficient of Determination)指标上的稳定性优于上述对比算法,平均提升了60.2%。本文所提出的算法对于山东省生猪市场的预测性能更优,有助于相关部门对生猪价格波动做出科学决策。展开更多
基金funding from the National Key Research and Development Program of China(2017YFB0202200)the Advanced Research Project of China(31511010203)+1 种基金Open Fund(201503-02)from State Key Laboratory of High Performance Computing,and Research Program of NUDT(ZK18-03-10).
文摘Exascale computing is one of the major challenges of this decade,and several studies have shown that communications are becoming one of the bottlenecks for scaling parallel applications.The analysis on the characteristics of communications can effectively aid to improve the performance of scientific applications.In this paper,we focus on the statistical regularity in time-dimension communication characteristics for representative scientific applications on supercomputer systems,and then prove that the distribution of communication-event intervals has a power-law decay,which is common in scientific interests and human activities.We verify the distribution of communication-event intervals has really a power-law decay on the Tianhe-2 supercomputer,and also on the other six parallel systems with three different network topologies and two routing policies.In order to do a quantitative study on the power-law distribution,we exploit two groups of statistics:bursty vs.memory and periodicity vs.dispersion.Our results indicate that the communication events show a“strong-bursty and weak-memory”characteristic and the communication event intervals show the periodicity and the dispersion.Finally,our research provides an insight into the relationship between communication optimizations and time-dimension communication characteristics.
文摘针对时变速度下的低碳配送需求,本文以配送总成本最小化为目标,构建考虑三维装载和时间窗约束的绿色车辆路径优化模型。模型考虑时变速度和实时载重对车辆燃油消耗量的影响。为准确计算行驶时间和油耗,采用二分K-means聚类算法对时段进行合理划分。设计两阶段算法求解模型:第一阶段采用自适应大规模邻域搜索(adaptive large neighborhood search,ALNS)算法以确定车辆配送路径;第二阶段采用遗传算法(genetic algorithm,GA)对货物进行三维装载顺序的可行性校验。算例结果表明,基于二分K-means聚类算法的时段划分方法能更精确地计算总成本,从而验证了本文所构建的模型和所设计的算法具有可行性和有效性。
文摘山东省是畜牧业大省,猪肉价格波动对居民生活质量有着重大影响,目前,关于山东省生猪价格波动的预测研究较少,且存在预测时间较短,时间窗口狭窄和预测结果不准确等问题。针对传统预测模型存在长时序预测准确率不足的问题,本文提出了一种基于综合决策机制的时间序列预测模型。首先,将时间序列信息进行分解,通过可逆归一化将数据特征进行放大,以提取更多的价格波动信息;在信息分解的基础上,通过上采样扩充先验知识,并采用多维度综合决策的方式,增强多层感知机的数据特征挖掘能力和决策能力;最后,将先验知识与预测结果进行直接映射,解决了窗口狭窄和滑动窗口迭代预测导致的误差累积问题。试验结果表明,相较于ARIMA、Prophet-BP、GA-BP、VMD-LSTM和STL-Informer模型,本文算法在RMSE(Root mean square error)和MAE(Mean absolute error)指标上平均提升了50.2%和30.9%,在R^(2)(Coefficient of Determination)指标上的稳定性优于上述对比算法,平均提升了60.2%。本文所提出的算法对于山东省生猪市场的预测性能更优,有助于相关部门对生猪价格波动做出科学决策。
