公开(公告)号：US20170214773A1

公开(公告)日：2017-07-27

申请号：US15299506

申请日：2016-10-21

Applicant: International Business Machines Corporation

Inventor： Liya Fan ,  Yong Deng Hu ,  He Yuan Huang ,  Chen Tian ,  Jian Wang ,  Zhe Yan ,  Ke Zhang

IPC: H04L29/06

CPC classification number: H03M7/40 ,  H03M7/3059 ,  H03M7/607 ,  H04L67/1097

Abstract: A method for optimizing migration efficiency of a data file over network is provided. Specifically, a total time of compression time of the data file, transfer time of the data file over the network, and decompression time of the data file, is minimized by adaptively selecting compression methods to compress each data block of the data file. For selecting a compression method for a data block, information entropy of the data block is analyzed, and a real status of computing and system resources is considered. Further, trade-off among the resource usage, compassion speed and compression ratio is made to calculate an optimized transmission solution over the network for each data block of the data file.

公开(公告)号：US20170139747A1

公开(公告)日：2017-05-18

申请号：US15415910

申请日：2017-01-26

Applicant: International Business Machines Corporation

Inventor： Ning Duan ,  Liya Fan ,  He Yuan Huang ,  Jian Wang ,  Zhi Hu Wang

IPC: G06F9/48 ,  G06F9/50

CPC classification number: G06F9/5083 ,  G06F9/4881 ,  G06F9/4887 ,  G06F2209/5019

Abstract: A method for scheduling MapReduce tasks includes receiving a set of task statistics corresponding to task execution within a MapReduce job, estimating a completion time for a set of tasks to be executed to provide an estimated completion time, calculating a soft decision point based on a convergence of a workload distribution corresponding to a set of executed tasks, calculating a hard decision point based on the estimated completion time for the set of tasks to be executed, determining a selected decision point based on the soft decision point and the hard decision point, and scheduling upcoming tasks for execution based on the selected decision point. The method may also include estimating a map task completion time and estimating a shuffle operation completion time. A computer program product and computer system corresponding to the method are also disclosed.

公开(公告)号：US20160026968A1

公开(公告)日：2016-01-28

申请号：US14339724

申请日：2014-07-24

Applicant: International Business Machines Corporation

Inventor： Liya Fan ,  Nicholas C. M. Fuller ,  Jian Qiu ,  Zhe Zhang

IPC: G06Q10/08 ,  G06F17/30

CPC classification number: G06Q10/087

Abstract: Automatically associating information technology resource patterns with specific information technology products by receiving a set of data about information technology assets, matching a subset of that data to a pattern in a set of patterns, determining that the subset of the data represents a product associated with that pattern, reporting this determination; receiving feedback on the accuracy of the determination, and updating pattern set information in response to that feedback.

Abstract translation: 通过接收关于信息技术资产的一组数据，将信息技术资源模式与特定信息技术产品自动关联，将该数据的一部分与一组模式中的模式相匹配，确定该数据子集代表与该模型相关联的产品 模式，报告这个决心; 接收关于确定精度的反馈，以及响应于该反馈来更新模式集信息。

公开(公告)号：US09852012B2

公开(公告)日：2017-12-26

申请号：US14835766

申请日：2015-08-26

Applicant: International Business Machines Corporation

Inventor： Ning Duan ,  Liya Fan ,  He Yuan Huang ,  Jian Wang ,  Zhi Hu Wang

IPC: G06F9/46 ,  G06F9/50 ,  G06F9/48

CPC classification number: G06F9/5083 ,  G06F9/4881 ,  G06F9/4887 ,  G06F2209/5019

Abstract: A method for scheduling MapReduce tasks includes receiving a set of task statistics corresponding to task execution within a MapReduce job, estimating a completion time for a set of tasks to be executed to provide an estimated completion time, calculating a soft decision point based on a convergence of a workload distribution corresponding to a set of executed tasks, calculating a hard decision point based on the estimated completion time for the set of tasks to be executed, determining a selected decision point based on the soft decision point and the hard decision point, and scheduling upcoming tasks for execution based on the selected decision point. The method may also include estimating a map task completion time and estimating a shuffle operation completion time. A computer program product and computer system corresponding to the method are also disclosed.

公开(公告)号：US09635512B2

公开(公告)日：2017-04-25

申请号：US14682215

申请日：2015-04-09

Applicant: International Business Machines Corporation

Inventor： Wen Hao An ,  Liya Fan ,  Bo Gao ,  Xi Sun ,  Yuzhou Zhang

IPC: H04W4/02 ,  G08G1/127 ,  G08G1/01 ,  H04B1/3822 ,  H04W28/06 ,  H03M7/40 ,  H04W64/00

CPC classification number: H04W4/029 ,  G08G1/0112 ,  G08G1/0129 ,  G08G1/127 ,  H03M7/40 ,  H03M7/4006 ,  H04B1/3822 ,  H04W28/06 ,  H04W64/00

Abstract: The invention relates to compressed data transmission in wireless data communication. Disclosed are methods and apparatuses for transporting residue of vehicle position data via a wireless network. A disclosed method for transporting residue of vehicle position data via a wireless network, includes the steps of: receiving data for updating residue encoding schema from a monitoring server; constructing a residue encoding schema based on the data, thereby producing a constructed residue encoding schema; and storing the constructed residue encoding schema such that the constructed residue encoding schema will become the current residue encoding schema; where: the constructed residue encoding schema is constructed such that each residue of the constructed residue encoding schema corresponds to a code; and the constructed residue encoding schema is constructed such that a residue having a relatively high probability of occurrence corresponds to a code of relatively short length.

公开(公告)号：US20170060630A1

公开(公告)日：2017-03-02

申请号：US14835766

申请日：2015-08-26

Applicant: International Business Machines Corporation

Inventor： Ning Duan ,  Liya Fan ,  He Yuan Huang ,  Jian Wang ,  Zhi Hu Wang

IPC: G06F9/48 ,  G06F9/50

CPC classification number: G06F9/5083 ,  G06F9/4881 ,  G06F9/4887 ,  G06F2209/5019

Abstract: A method for scheduling MapReduce tasks includes receiving a set of task statistics corresponding to task execution within a MapReduce job, estimating a completion time for a set of tasks to be executed to provide an estimated completion time, calculating a soft decision point based on a convergence of a workload distribution corresponding to a set of executed tasks, calculating a hard decision point based on the estimated completion time for the set of tasks to be executed, determining a selected decision point based on the soft decision point and the hard decision point, and scheduling upcoming tasks for execution based on the selected decision point. The method may also include estimating a map task completion time and estimating a shuffle operation completion time. A computer program product and computer system corresponding to the method are also disclosed.

公开(公告)号：US09891950B2

公开(公告)日：2018-02-13

申请号：US15415910

申请日：2017-01-26

Applicant: International Business Machines Corporation

Inventor： Ning Duan ,  Liya Fan ,  He Yuan Huang ,  Jian Wang ,  Zhi Hu Wang

IPC: G06F9/46 ,  G06F9/48 ,  G06F9/50

CPC classification number: G06F9/5083 ,  G06F9/4881 ,  G06F9/4887 ,  G06F2209/5019

Abstract: A method for scheduling MapReduce tasks includes receiving a set of task statistics corresponding to task execution within a MapReduce job, estimating a completion time for a set of tasks to be executed to provide an estimated completion time, calculating a soft decision point based on a convergence of a workload distribution corresponding to a set of executed tasks, calculating a hard decision point based on the estimated completion time for the set of tasks to be executed, determining a selected decision point based on the soft decision point and the hard decision point, and scheduling upcoming tasks for execution based on the selected decision point. The method may also include estimating a map task completion time and estimating a shuffle operation completion time. A computer program product and computer system corresponding to the method are also disclosed.

公开(公告)号：US09521218B1

公开(公告)日：2016-12-13

申请号：US15002421

申请日：2016-01-21

Applicant: International Business Machines Corporation

Inventor： Liya Fan ,  Yong Deng Hu ,  He Yuan Huang ,  Chen Tian ,  Jian Wang ,  Zhe Yan ,  Ke Zhang

IPC: G06F15/16 ,  H04L29/06 ,  H04L29/08 ,  H03M7/30 ,  H03M7/40

CPC classification number: H03M7/40 ,  H03M7/3059 ,  H03M7/607 ,  H04L67/1097

Abstract: A method for optimizing migration efficiency of a data file over network is provided. Specifically, a total time of compression time of the data file, transfer time of the data file over the network, and decompression time of the data file, is minimized by adaptively selecting compression methods to compress each data block of the data file. For selecting a compression method for a data block, information entropy of the data block is analyzed, and a real status of computing and system resources is considered. Further, trade-off among the resource usage, compassion speed and compression ratio is made to calculate an optimized transmission solution over the network for each data block of the data file.

Abstract translation: 提供了一种通过网络优化数据文件的迁移效率的方法。 具体地，通过自适应地选择压缩方法来压缩数据文件的每个数据块，使数据文件的压缩时间的总时间，数据文件在网络上的传送时间和数据文件的解压缩时间被最小化。 为了选择数据块的压缩方法，分析数据块的信息熵，并考虑计算和系统资源的真实状态。 此外，在资源使用，同情速度和压缩比之间进行权衡，以对数据文件的每个数据块计算网络上优化的传输解决方案。

公开(公告)号：US09411645B1

公开(公告)日：2016-08-09

申请号：US14982296

申请日：2015-12-29

Applicant: International Business Machines Corporation

Inventor： Ning Duan ,  Liya Fan ,  He Yuan Huang ,  Jian Wang ,  Zhi Hu Wang

IPC: G06F9/46 ,  G06F9/48 ,  G06F9/50

CPC classification number: G06F9/5083 ,  G06F9/4881 ,  G06F9/4887 ,  G06F2209/5019

Abstract: A method for scheduling MapReduce tasks includes receiving a set of task statistics corresponding to task execution within a MapReduce job, estimating a completion time for a set of tasks to be executed to provide an estimated completion time, calculating a soft decision point based on a convergence of a workload distribution corresponding to a set of executed tasks, calculating a hard decision point based on the estimated completion time for the set of tasks to be executed, determining a selected decision point based on the soft decision point and the hard decision point, and scheduling upcoming tasks for execution based on the selected decision point. The method may also include estimating a map task completion time and estimating a shuffle operation completion time. A computer program product and computer system corresponding to the method are also disclosed.

Abstract translation: 一种用于调度MapReduce任务的方法包括：接收与MapReduce作业内的任务执行相对应的一组任务统计信息，估计要执行的一组任务的完成时间以提供估计的完成时间，基于收敛计算软判决点 对应于一组执行任务的工作负载分布，基于所述待执行的任务集合的估计完成时间计算硬判决点，基于所述软判决点和所述硬判决点确定所选择的判定点;以及 根据所选择的决策点安排即将到来的执行任务。 该方法还可以包括估计地图任务完成时间并估计洗牌操作完成时间。 还公开了一种对应于该方法的计算机程序产品和计算机系统。

公开(公告)号：US20130311480A1

公开(公告)日：2013-11-21

申请号：US13868559

申请日：2013-04-23

Applicant: International Business Machines Corporation

Inventor： Wen Hao An ,  Ning Duan ,  Liya Fan ,  Bo Gao ,  Ke Hu ,  Wei Sun ,  Yu Ying Wang ,  Zhi Hu Wang

IPC: G06F17/30

CPC classification number: G06F17/30106 ,  G06F17/30091

Abstract: A method, an apparatus, and a system for locating sensor data. The method includes the steps of: obtaining an index table; intercepting a query for sensor data in runtime; extracting a characteristic parameter from a query condition; locating a block identifier of matching sensor data storage blocks in the index table by using the characteristic parameter; and loading the storage blocks into a memory space of a working processor; where the index table contains mapping relationships between block identifiers of sensor data storage blocks and characteristic attributes of sensor data.

Abstract translation: 一种用于定位传感器数据的方法，装置和系统。 该方法包括以下步骤：获得索引表; 在运行时拦截传感器数据查询; 从查询条件提取特征参数; 通过使用特征参数，将索引表中的匹配传感器数据存储块的块标识符定位; 并将所述存储块加载到工作处理器的存储器空间中; 其中索引表包含传感器数据存储块的块标识符与传感器数据的特性属性之间的映射关系。