-
1.发明授权System and method for automated and adaptive threshold setting to separately control false positive and false negative performance prediction errors 失效用于自动和自适应阈值设置的系统和方法，以分别控制假阳性和假阴性预测误差公开(公告)号：US08037365B2
公开(公告)日：2011-10-11
申请号：US12611134
申请日：2009-11-03
IPC分类号： G06F11/00
CPC分类号： G06F11/008
摘要： Managing a computer system including automatically adjusting two separate component thresholds (a component threshold pair) based on a statistical model. Specifically, a first component threshold is modeled to predict violations of an SLO based on a violation of the first component threshold and a second, separate component threshold is modeled to predict a non-violation (compliance) of an SLO based on a non-violation of the second component threshold. Over time, the values of the component thresholds may change and one component threshold may be greater than the other component threshold at one time, and vice versa at another time. A component metric reading between the first and second component thresholds indicates that a prediction of an SLO violation or compliance is less certain, and a warning may be issued rather than an alert.
摘要翻译： 管理计算机系统，包括基于统计模型自动调整两个单独的组件阈值（组件阈值对）。 具体地说，第一组件阈值被建模以基于违反第一组件阈值来预测SLO的违规，并且第二单独的组件阈值被建模以基于非违规来预测SLO的非违规（依从性） 的第二分量阈值。 随着时间的推移，组件阈值的值可能会改变，一个组件阈值可能会同时大于另一组件阈值，反之亦然。 在第一和第二组件阈值之间的组件度量读数表示SLO违规或合规性的预测不太确定，并且可以发出警告而不是警报。
-
2.发明申请SYSTEM AND METHOD FOR AUTOMATED AND ADAPTIVE THRESHOLD SETTING TO SEPARATELY CONTROL FALSE POSITIVE AND FALSE NEGATIVE PERFORMANCE PREDICTION ERRORS 失效用于自动和自适应阈值的系统和方法设置为分别控制假阳性和假阴性性能预测误差公开(公告)号：US20110107154A1
公开(公告)日：2011-05-05
申请号：US12611134
申请日：2009-11-03
CPC分类号： G06F11/008
摘要： Managing a computer system including automatically adjusting two separate component thresholds (a component threshold pair) based on a statistical model. Specifically, a first component threshold is modeled to predict violations of an SLO based on a violation of the first component threshold and a second, separate component threshold is modeled to predict a non-violation (compliance) of an SLO based on a non-violation of the second component threshold. Over time, the values of the component thresholds may change and one component threshold may be greater than the other component threshold at one time, and vice versa at another time. A component metric reading between the first and second component thresholds indicates that a prediction of an SLO violation or compliance is less certain, and a warning may be issued rather than an alert.
摘要翻译： 管理计算机系统，包括基于统计模型自动调整两个单独的组件阈值（组件阈值对）。 具体地，第一组件阈值被建模以基于违反第一组件阈值来预测违反SLO，并且第二单独组件阈值被建模以基于非违规来预测SLO的非违规（顺从性） 的第二分量阈值。 随着时间的推移，组件阈值的值可能会改变，一个组件阈值可能会同时大于另一组件阈值，反之亦然。 在第一和第二组件阈值之间的组件度量读数表示SLO违规或合规性的预测不太确定，并且可以发出警告而不是警报。
-
公开(公告)号：US08326660B2
公开(公告)日：2012-12-04
申请号：US11969927
申请日：2008-01-07
CPC分类号： G06Q30/02 , G06Q10/0639
摘要： A method for maximizing a utility of a service contract by optimizing target response time for a performance service level objective is provided. A set of criteria are provided to ensure that performance requirements for the service are met. The method comprises determining one or more usage windows for providing a service, wherein each usage window is associated with a performance requirement and a time period; extracting usage patterns for each usage window based on historical data provided from monitoring requests for service in each usage window; extracting response time per transaction associated with said requests based on historical data provided from monitoring responses provided to said requests in each usage window; and calculating optimal probability for breach in each usage window (Pi) and determining the associated target response time, based on the usage pattern for each window and the response time per transaction.
摘要翻译： 提供了一种通过优化性能服务级别目标的目标响应时间来最大化服务契约效用的方法。 提供了一套标准，以确保满足服务的性能要求。 该方法包括确定用于提供服务的一个或多个使用窗口，其中每个使用窗口与性能要求和时间段相关联; 基于从每个使用窗口中的监视服务请求提供的历史数据，提取每个使用窗口的使用模式; 基于从提供给每个使用窗口中的所述请求的监视响应提供的历史数据来提取与所述请求相关联的每个事务的响应时间; 以及基于每个窗口的使用模式和每个事务的响应时间，计算每个使用窗口（Pi）中的违规的最佳概率并确定相关联的目标响应时间。
-
公开(公告)号：US20090177507A1
公开(公告)日：2009-07-09
申请号：US11969927
申请日：2008-01-07
CPC分类号： G06Q30/02 , G06Q10/0639
摘要： A method for maximizing a utility of a service contract by optimizing target response time for a performance service level objective is provided. A set of criteria are provided to ensure that performance requirements for the service are met. The method comprises determining one or more usage windows for providing a service, wherein each usage window is associated with a performance requirement and a time period; extracting usage patterns for each usage window based on historical data provided from monitoring requests for service in each usage window; extracting response time per transaction associated with said requests based on historical data provided from monitoring responses provided to said requests in each usage window; and calculating optimal probability for breach in each usage window (Pi) and determining the associated target response time, based on the usage pattern for each window and the response time per transaction.
摘要翻译： 提供了一种通过优化性能服务级别目标的目标响应时间来最大化服务契约效用的方法。 提供了一套标准，以确保满足服务的性能要求。 该方法包括确定用于提供服务的一个或多个使用窗口，其中每个使用窗口与性能要求和时间段相关联; 基于从每个使用窗口中的监视服务请求提供的历史数据，提取每个使用窗口的使用模式; 基于从提供给每个使用窗口中的所述请求的监视响应提供的历史数据来提取与所述请求相关联的每个事务的响应时间; 以及基于每个窗口的使用模式和每个事务的响应时间，计算每个使用窗口（Pi）中的违规的最佳概率并确定相关联的目标响应时间。
-
5.发明授权公开(公告)号：US09276759B2
公开(公告)日：2016-03-01
申请号：US11845750
申请日：2007-08-27
IPC分类号： G06F15/173 , H04L12/26 , H04L12/24 , H04L12/28
CPC分类号： H04L43/0805 , H04L12/2807 , H04L41/12 , H04L43/00
摘要： In a typical computer network, at least some of the managed resources are monitored to determine whether those resources are meeting predetermined performance goals or service level objectives. To simplify the process of configuring a network monitor, information about the service level objectives is loaded into the resource itself. When the resource is detected, the service level objective information is extracted from the resource information and made available to a translating engine. The translating engine converts the extracted information to monitoring directions that are used to configure the network monitor. Embodiments in which new resources are detected either buying a registration process or a polling process are described.
摘要翻译： 在典型的计算机网络中，监视至少一些被管理资源以确定这些资源是否满足预定的性能目标或服务级目标。 为了简化配置网络监视器的过程，有关服务级别目标的信息将加载到资源本身中。 当检测到资源时，从资源信息中提取服务级目标信息，并使其可用于翻译引擎。 翻译引擎将提取的信息转换为用于配置网络监视器的监视方向。 描述了检测到新资源的购买注册过程或轮询过程的实施例。
-
6.发明授权Method, system and program product for detecting an operational risk of a node 失效用于检测节点操作风险的方法，系统和程序产品公开(公告)号：US07529842B2
公开(公告)日：2009-05-05
申请号：US10321265
申请日：2002-12-17
IPC分类号： G06F15/16
CPC分类号： G06F11/008 , G06F11/3409
摘要： Under the present invention, the performances of a plurality of similarly configured nodes are monitored and compared. If one of the nodes exhibits a performance that varies from the performances of the other nodes by more than a current tolerance, an operational risk is detected. If detected, an alert can be generated and one or more corrective actions implemented to address the operational risk.
摘要翻译： 在本发明中，监视和比较多个类似配置的节点的性能。 如果其中一个节点表现出与其他节点的性能不同的性能超过当前公差，则会检测到操作风险。 如果检测到，可以生成警报并实施一个或多个纠正措施来解决操作风险。
-
公开(公告)号：US20090094488A1
公开(公告)日：2009-04-09
申请号：US12337179
申请日：2008-12-17
IPC分类号： G06F11/34
CPC分类号： G06F11/008 , G06F11/3452
摘要： A system and method for monitoring the availability of an application in a distributed data processing environment are provided. The performance aspects of application availability are defined in terms of easily observed and computed characteristics of the application as it behaves in a deployed environment with the deployed configuration. The system and method observe the application processes, the structural resources they require, and the consumable resources they require from the running system itself. These observations are then used to derive minimum requirements for the resource requirement aspects of availability as well as derive criteria for normal behavioral conditions. These minimum requirements and normal behavioral conditions are then used to establish monitoring rules or conditions for monitoring the operation of the application to determine if availability of the application is degrading such that a notification needs to be sent to an administrator.
摘要翻译： 提供了一种用于在分布式数据处理环境中监视应用程序的可用性的系统和方法。 应用程序可用性的性能方面是根据应用程序容易观察和计算的特性来定义的，因为它在部署的配置环境中的行为。 系统和方法观察应用过程，需要的结构资源以及运行系统本身所需的可消耗资源。 然后，这些观察结果用于获得资源需求方面对可用性的最低要求，并得出正常行为条件的标准。 然后将这些最低要求和正常行为条件用于建立监控应用程序操作的监控规则或条件，以确定应用程序的可用性是否有降级，以便通知需要发送给管理员。
-
公开(公告)号：US07480834B2
公开(公告)日：2009-01-20
申请号：US11030249
申请日：2005-01-06
IPC分类号： G06F11/00
CPC分类号： G06F11/008 , G06F11/3452
摘要： A system and method for monitoring the availability of an application in a distributed data processing environment are provided. The performance aspects of application availability are defined in terms of easily observed and computed characteristics of the application as it behaves in a deployed environment with the deployed configuration. The system and method observe the application processes, the structural resources they require, and the consumable resources they require from the running system itself. These observations are then used to derive minimum requirements for the resource requirement aspects of availability as well as derive criteria for normal behavioral conditions. These minimum requirements and normal behavioral conditions are then used to establish monitoring rules or conditions for monitoring the operation of the application to determine if availability of the application is degrading such that a notification needs to be sent to an administrator.
摘要翻译： 提供了一种用于在分布式数据处理环境中监视应用程序的可用性的系统和方法。 应用程序可用性的性能方面是根据应用程序容易观察和计算的特性来定义的，因为它在部署的配置环境中的行为。 系统和方法观察应用过程，需要的结构资源以及运行系统本身所需的可消耗资源。 然后，这些观察结果用于获得资源需求方面对可用性的最低要求，并得出正常行为条件的标准。 然后将这些最低要求和正常行为条件用于建立监控应用程序操作的监控规则或条件，以确定应用程序的可用性是否有降级，以便通知需要发送给管理员。
-
公开(公告)号：US20090048998A1
公开(公告)日：2009-02-19
申请号：US12136792
申请日：2008-06-11
IPC分类号： G06N5/00
CPC分类号： G06N5/025
摘要： A context-sensitive pre-evaluation analysis of a set of rules is performed based on the circumstance or the current state of a rule clause directed to an infrequently changing condition. A group of multiple-clause rules are identified which each have a clause defining an infrequently changing condition for evaluating a state of a resource. The current state of the resource is monitored. If the identified group of multiple-clause rules, which cannot evaluate as TRUE under the context of the current state the resource, the identified group of multiple-clause rules are excluded from consideration by the rules engine. The rules engine will then encounter fewer rules to evaluate for a solution. The identified group of multiple-clause rules is further analyzed in the context of the infrequently changing condition for the current resource state. State metrics that are defined by clauses of the identified multiple-clause rules, those that cannot evaluate as TRUE, are identified. Those metrics are then also excluded from consideration by the rules engine. Thus, the rules engine will encounter fewer rules and/or event states that cannot be evaluated to a solution. The context-sensitive pre-evaluation analysis of the rules is performed out-of-band as the rules engine traverses the rule.
摘要翻译： 基于针对不经常变化的条件的规则子句的情况或当前状态来执行一组规则的上下文敏感的预评估分析。 识别一组多子句规则，每个子句都有一个子句定义用于评估资源状态的不常变化的条件。 监视资源的当前状态。 如果在当前状态资源的上下文中不能评估为TRUE的多个子句规则的标识组，则由规则引擎排除所识别的多条款规则组。 然后，规则引擎将会遇到更少的规则来评估解决方案。 在当前资源状态的不频繁变化的条件的上下文中进一步分析所识别的多子句规则组。 识别由所识别的多条款规则的条款定义的状态度量，不能评估为TRUE的状态指标。 那些指标也被排除在规则引擎的考虑之外。 因此，规则引擎将遇到更少的规则和/或事件状态，无法对解决方案进行评估。 当规则引擎遍历规则时，规则的上下文敏感的预评估分析是在带外执行的。
-
公开(公告)号：US07412432B2
公开(公告)日：2008-08-12
申请号：US11260815
申请日：2005-10-27
CPC分类号： G06N5/025
摘要： A context-sensitive pre-evaluation analysis of a set of rules is performed based on the circumstance or the current state of a rule clause directed to an infrequently changing condition. A group of multiple-clause rules are identified which each have a clause defining an infrequently changing condition for evaluating a state of a resource. The current state of the resource is monitored. If the identified group of multiple-clause rules, which cannot evaluate as TRUE under the context of the current state the resource, the identified group of multiple-clause rules are excluded from consideration by the rules engine. The rules engine will then encounter fewer rules to evaluate for a solution. The identified group of multiple-clause rules is further analyzed in the context of the infrequently changing condition for the current resource state. State metrics that are defined by clauses of the identified multiple-clause rules, those that cannot evaluate as TRUE, are identified. Those metrics are then also excluded from consideration by the rules engine. Thus, the rules engine will encounter fewer rules and/or event states that cannot be evaluated to a solution. The context-sensitive pre-evaluation analysis of the rules is performed out-of-band as the rules engine traverses the rule.
摘要翻译： 基于针对不经常变化的条件的规则子句的情况或当前状态来执行一组规则的上下文敏感的预评估分析。 识别一组多子句规则，每个子句都有一个子句定义用于评估资源状态的不常变化的条件。 监视资源的当前状态。 如果在当前状态资源的上下文中不能评估为TRUE的多个子句规则的标识组，则由规则引擎排除所识别的多条款规则组。 然后，规则引擎将会遇到更少的规则来评估解决方案。 在当前资源状态的不频繁变化的条件的上下文中进一步分析所识别的多子句规则组。 识别由所识别的多条款规则的条款定义的状态度量，不能评估为TRUE的状态指标。 那些指标也被排除在规则引擎的考虑之外。 因此，规则引擎将遇到更少的规则和/或事件状态，无法对解决方案进行评估。 当规则引擎遍历规则时，规则的上下文敏感的预评估分析是在带外执行的。
-
-
-
-
-
-
-
-
-
搜索结果
30 条记录 (耗时 0.024 秒)
