利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

57 条记录 (耗时 0.048 秒)

    Systems and methods for providing constrained optimization using adaptive regulatory control
    1.
    发明授权
    Systems and methods for providing constrained optimization using adaptive regulatory control 有权
    使用自适应调节控制提供约束优化的系统和方法

    公开(公告)号：US07346401B2

    公开(公告)日：2008-03-18

    申请号：US10853845

    申请日：2004-05-25

    申请人： Yixin Diao ,  Christian Marcelo Garcia-Arellano ,  Joseph L. Hellerstein ,  Sam Sampson Lightstone ,  Sujay Sunil Parekh ,  Adam J. Storm ,  Maheswaran Surendra

    发明人： Yixin Diao ,  Christian Marcelo Garcia-Arellano ,  Joseph L. Hellerstein ,  Sam Sampson Lightstone ,  Sujay Sunil Parekh ,  Adam J. Storm ,  Maheswaran Surendra

    IPC分类号： G05B13/02

    CPC分类号： G06F9/5083

    摘要： Systems and methods are provided for optimizing the performance and/or allocation of constrained resources in a dynamic computing environment using adaptive regulatory control methods. For example, systems and methods for providing constrained optimization in a dynamic computing system implement model-based adaptive (self-tuning) regulatory control schemes that are designed to handle the system dynamics and which take into consideration control costs (such as the overheads of changing resource allocations and performance degradation due to transient load imbalances) to find an optimal solution. To facilitate practical application, a dual control architecture is disclosed which combines a heuristic fixed step control process that is implemented when there is no valid system model for model-based control. A system model is continually obtained and validated during run-time to adapt control parameters to variations in system dynamics.

    摘要翻译： 提供的系统和方法用于使用自适应调节控制方法来优化动态计算环境中约束资源的性能和/或分配。 例如，用于在动态计算系统中提供约束优化的系统和方法实施基于模型的自适应（自调节）调节控制方案，其被设计为处理系统动态并考虑到控制成本（例如变化的开销 资源分配和由于瞬态负载不平衡引起的性能下降），以找到最佳解决方案。 为了便于实际应用，公开了一种双控制架构，其结合了当没有用于基于模型的控制的有效系统模型时实现的启发式固定步长控制过程。 系统模型在运行期间不断获得和验证，以使控制参数适应系统动态变化。

    METHOD AND APPARATUS FOR ONLINE SAMPLE INTERVAL DETERMINATION
    2.
    发明申请
    METHOD AND APPARATUS FOR ONLINE SAMPLE INTERVAL DETERMINATION 失效
    在线样品间隔测定的方法和装置

    公开(公告)号：US20080263563A1

    公开(公告)日：2008-10-23

    申请号：US12165009

    申请日：2008-06-30

    申请人： Yixin Diao ,  Joseph L. Hellerstein ,  Sam Sampson Lightstone ,  Adam J. Storm ,  Maheswaran Surendra

    发明人： Yixin Diao ,  Joseph L. Hellerstein ,  Sam Sampson Lightstone ,  Adam J. Storm ,  Maheswaran Surendra

    IPC分类号： G06F9/50

    CPC分类号： G06F11/3495 ,  G06F9/5016 ,  G06F9/5033 ,  G06F11/3419 ,  G06F11/3452 ,  G06F2201/87

    摘要： In one embodiment, functional system elements are added to an autonomic manager to enable automatic online sample interval selection. In another embodiment, a method for determining the sample interval by continually characterizing the system workload behavior includes monitoring the system data and analyzing the degree to which the workload is stationary. This makes the online optimization method less sensitive to system noise and capable of being adapted to handle different workloads. The effectiveness of the autonomic optimizer is thereby improved, making it easier to manage a wide range of systems.

    摘要翻译： 在一个实施例中，将功能系统元件添加到自主管理器以启用自动在线采样间隔选择。 在另一个实施例中，用于通过连续地表征系统工作负载行为来确定采样间隔的方法包括监视系统数据并分析工作负载静止的程度。 这使得在线优化方法对系统噪声不太敏感，并且能够适应于处理不同的工作负载。 从而改进了自主优化器的有效性，从而更容易地管理广泛的系统。

    METHOD AND APPARATUS FOR ONLINE SAMPLE INTERVAL DETERMINATION
    3.
    发明申请
    METHOD AND APPARATUS FOR ONLINE SAMPLE INTERVAL DETERMINATION 审中-公开
    在线样品间隔测定的方法和装置

    公开(公告)号：US20130013785A1

    公开(公告)日：2013-01-10

    申请号：US13617901

    申请日：2012-09-14

    申请人： YIXIN DIAO ,  Joseph L. Hellerstein ,  Sam Sampson Lightstone ,  Adam J. Storm ,  Maheswaran Surendra

    发明人： YIXIN DIAO ,  Joseph L. Hellerstein ,  Sam Sampson Lightstone ,  Adam J. Storm ,  Maheswaran Surendra

    IPC分类号： G06F15/173

    CPC分类号： G06F11/3495 ,  G06F9/5016 ,  G06F9/5033 ,  G06F11/3419 ,  G06F11/3452 ,  G06F2201/87

    摘要： In one embodiment, functional system elements are added to an autonomic manager to enable automatic online sample interval selection. In another embodiment, a method for determining the sample interval by continually characterizing the system workload behavior includes monitoring the system data and analyzing the degree to which the workload is stationary. This makes the online optimization method less sensitive to system noise and capable of being adapted to handle different workloads. The effectiveness of the autonomic optimizer is thereby improved, making it easier to manage a wide range of systems.

    摘要翻译： 在一个实施例中，将功能系统元件添加到自主管理器以启用自动在线采样间隔选择。 在另一个实施例中，用于通过连续地表征系统工作负载行为来确定采样间隔的方法包括监视系统数据并分析工作负载静止的程度。 这使得在线优化方法对系统噪声不太敏感，并且能够适应于处理不同的工作负载。 从而改进了自主优化器的有效性，从而更容易地管理广泛的系统。

    Method and system for combining multiple benchmarks
    6.
    发明授权
    Method and system for combining multiple benchmarks 有权
    组合多个基准的方法和系统

    公开(公告)号：US09064038B2

    公开(公告)日：2015-06-23

    申请号：US11511968

    申请日：2006-08-29

    申请人： Aaron B. Brown ,  Joseph L. Hellerstein ,  Tsz-Kin Lau ,  Sam Sampson Lightstone ,  Carolyn Haibt Norton ,  Peter K. L. Shum ,  William H. Tetzlaff

    发明人： Aaron B. Brown ,  Joseph L. Hellerstein ,  Tsz-Kin Lau ,  Sam Sampson Lightstone ,  Carolyn Haibt Norton ,  Peter K. L. Shum ,  William H. Tetzlaff

    IPC分类号： G06F9/44 ,  G06F11/34

    CPC分类号： G06F11/3428

    摘要： Techniques are disclosed for combining multiple benchmarks for use in assessing characteristics of a computing system. For example, a method for configuring and running multiple benchmarks includes the following steps. A multiple benchmark specification is obtained. The multiple benchmark specification includes multiple individual benchmark specifications and a multiple benchmark workflow describing an ordering according to which the multiple individual benchmarks are to be configured and run. The multiple benchmarks are configured and run according to the ordering identified in the multiple benchmark workflow. Results of the multiple benchmark runs are recorded. One or more specifications or results associated with at least one of the multiple benchmarks are utilized as part of a benchmark specification for at least another of the multiple benchmarks so as to provide consistency between at least the one and the other of the multiple benchmarks.

    摘要翻译： 公开了用于组合用于评估计算系统的特性的多个基准的技术。 例如，一种用于配置和运行多个基准测试的方法包括以下步骤。 获得多重基准规范。 多个基准测试规范包括多个单独的基准测试规范和多个基准测试工作流程，描述根据多个单独的基准来配置和运行的排序。 多个基准测试根据多基准工作流程中确定的顺序进行配置和运行。 记录多个基准测试的结果。 与多个基准中的至少一个相关联的一个或多个规范或结果被用作多个基准中的至少另一个的基准规范的一部分，以便提供多个基准中的至少一个和另一个之间的一致性。

    Method and system for combining multiple benchmarks
    7.
    发明申请
    Method and system for combining multiple benchmarks 有权
    组合多个基准的方法和系统

    公开(公告)号：US20080127083A1

    公开(公告)日：2008-05-29

    申请号：US11511968

    申请日：2006-08-29

    申请人： Aaron B. Brown ,  Joseph L. Hellerstein ,  Tsz-Kin Lau ,  Sam Sampson Lightstone ,  Carolyn Haibt Norton ,  Peter K.L. Shum ,  William H. Tetzlaff

    发明人： Aaron B. Brown ,  Joseph L. Hellerstein ,  Tsz-Kin Lau ,  Sam Sampson Lightstone ,  Carolyn Haibt Norton ,  Peter K.L. Shum ,  William H. Tetzlaff

    IPC分类号： G06F9/44

    CPC分类号： G06F11/3428

    摘要： Techniques are disclosed for combining multiple benchmarks for use in assessing characteristics of a computing system. For example, a method for configuring and running multiple benchmarks includes the following steps. A multiple benchmark specification is obtained. The multiple benchmark specification includes multiple individual benchmark specifications and a multiple benchmark workflow describing an ordering according to which the multiple individual benchmarks are to be configured and run. The multiple benchmarks are configured and run according to the ordering identified in the multiple benchmark workflow. Results of the multiple benchmark runs are recorded. One or more specifications or results associated with at least one of the multiple benchmarks are utilized as part of a benchmark specification for at least another of the multiple benchmarks so as to provide consistency between at least the one and the other of the multiple benchmarks.

    摘要翻译： 公开了用于组合用于评估计算系统的特性的多个基准的技术。 例如，一种用于配置和运行多个基准测试的方法包括以下步骤。 获得多重基准规范。 多个基准测试规范包括多个单独的基准测试规范和多个基准测试工作流程，描述根据多个单独的基准来配置和运行的排序。 多个基准测试根据多基准工作流程中确定的顺序进行配置和运行。 记录多个基准测试的结果。 与多个基准中的至少一个相关联的一个或多个规范或结果被用作多个基准中的至少另一个的基准规范的一部分，以便提供多个基准中的至少一个和另一个之间的一致性。

    Methods and apparatus for performing adaptive and robust prediction
    9.
    发明授权
    Methods and apparatus for performing adaptive and robust prediction 失效
    用于执行自适应和鲁棒预测的方法和装置

    公开(公告)号：US07039559B2

    公开(公告)日：2006-05-02

    申请号：US10385265

    申请日：2003-03-10

    申请人： Steven E. Froehlich ,  Joseph L. Hellerstein ,  Edwin Richie Lassettre ,  Todd William Mummert ,  Maheswaran Surendra

    发明人： Steven E. Froehlich ,  Joseph L. Hellerstein ,  Edwin Richie Lassettre ,  Todd William Mummert ,  Maheswaran Surendra

    IPC分类号： G06F3/05

    CPC分类号： G06F9/5083 ,  G06F2209/5019

    摘要： Techniques for performing adaptive and robust prediction. Prediction techniques are adaptive in that they use a minimal amount of historical data to make predictions, the amount of data being selectable. The techniques are able to learn quickly about changes in the workload traffic pattern and make predictions, based on such learning, that are useful for proactive response to workload changes. To counter the increased variability in the prediction as a result of using minimal history, robustness is improved by checking model stability at every time interval and revising the model structure as needed to meet designated stability criteria. Furthermore, the short term prediction techniques can be used in conjunction with a long term forecaster.

    摘要翻译： 用于执行自适应和鲁棒预测的技术。 预测技术是自适应的，因为它们使用最少量的历史数据进行预测，数据量可选择。 这些技术能够快速了解​​工作负载流量模式的变化，并根据此类学习进行预测，对于对工作负载变化的主动响应非常有用。 为了应对由于使用最小历史而导致的预测增加的变异性，通过在每个时间间隔检查模型稳定性并根据需要修改模型结构来改善鲁棒性以满足指定的稳定性标准。 此外，短期预测技术可以与长期预报员结合使用。

    Resource Optimizations in Computing Utilities
    10.
    发明申请
    Resource Optimizations in Computing Utilities 有权
    计算实用程序中的资源优化

    公开(公告)号：US20080313160A1

    公开(公告)日：2008-12-18

    申请号：US12197593

    申请日：2008-08-25

    申请人： Joseph L. Hellerstein ,  Kaan Katircioglu ,  Maheswaran Surendra

    发明人： Joseph L. Hellerstein ,  Kaan Katircioglu ,  Maheswaran Surendra

    IPC分类号： G06F17/30

    CPC分类号： G06Q10/06 ,  Y10S707/99933 ,  Y10S707/99935 ,  Y10S707/99943

    摘要： Techniques are provided for use in accordance with relates to computing utilities. For example, in one aspect of the invention, a method for use in a computing utility, wherein the computing utility comprises a plurality of application service provider systems and a utility controller, and each application service provider system comprising an application controller, comprises the following steps. An application request to one of the plurality of application service provider systems is obtained. Then, in response to the application request, at least one of: (i) the application controller of the application service provider system to which the application request is directed computes a value of a business metric associated with a resource action; and (ii) the utility controller computes a value of a business metric associated with a resource action.

    摘要翻译： 根据与计算实用程序有关的技术被提供用于使用。 例如，在本发明的一个方面，一种在计算实用程序中使用的方法，其中所述计算实用程序包括多个应用服务提供者系统和效用控制器，并且包括应用控制器的每个应用服务提供商系统包括以下 脚步。 获得对多个应用服务提供商系统之一的应用请求。 然后，响应于所述应用请求，至少一个：（i）应用请求所针对的应用服务提供商系统的应用控制器计算与资源动作相关联的业务量度的值; 和（ii）公用事业控制器计算与资源动作相关联的业务度量的值。