利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

331 条记录 (耗时 0.019 秒)

    HIERARCHICAL ENERGY OPTIMIZATION FOR DATACENTER NETWORKS
    1.
    发明申请
    HIERARCHICAL ENERGY OPTIMIZATION FOR DATACENTER NETWORKS 有权
    DATACENTER网络的分层能量优化

    公开(公告)号：US20140047252A1

    公开(公告)日：2014-02-13

    申请号：US13819267

    申请日：2012-05-21

    申请人： Nirwan Ansari ,  Yan Zhang

    发明人： Nirwan Ansari ,  Yan Zhang

    IPC分类号： G06F1/32

    CPC分类号： G06F1/32 ,  G06F1/26 ,  G06F1/3203 ,  G06F1/3278 ,  G06F1/3287 ,  Y02D10/157 ,  Y02D10/171

    摘要： Technologies are presented for power optimization of datacenter networks in a hierarchical perspective. In some examples, a two-level power optimization model may be established to reduce the power consumption of datacenter networks by switching off network switches and links while still guaranteeing full connectivity and maximum link utilization. The model may be implemented by solving a capacitated constraint multi-commodity flow (CMCF) problem employing simple heuristic techniques. A power status of network switches may be determined according to a network traffic matrix and the CMCF optimization determined at core-level and at pod-level. A complementary process to provision whole network connectivity and to meet quality of service (QoS) goals may also be performed.

    摘要翻译： 针对数据中心网络的功能优化技术进行了分层分析。 在一些示例中，可以建立两级功率优化模型，以通过关闭网络交换机和链路来减少数据中心网络的功耗，同时仍然保证完全连接和最大链路利用率。 该模型可以通过使用简单的启发式技术来求解容许约束多商品流（CMCF）问题来实现。 网络交换机的电源状态可以根据网络流量矩阵确定，CMCF优化在核心级别和pod级确定。 也可以执行提供整个网络连接和满足服务质量（QoS）目标的补充过程。

    FAIR QUANTIZED CONGESTION NOTIFICATION (FQCN) TO MITIGATE TRANSPORT CONTROL PROTOCOL (TCP) THROUGHPUT COLLAPSE IN DATA CENTER NETWORKS
    2.
    发明申请
    FAIR QUANTIZED CONGESTION NOTIFICATION (FQCN) TO MITIGATE TRANSPORT CONTROL PROTOCOL (TCP) THROUGHPUT COLLAPSE IN DATA CENTER NETWORKS 有权
    公平的量化协议通知（FQCN）在数据中心网络中减少运输控制协议（TCP）通过吞吐量

    公开(公告)号：US20130124753A1

    公开(公告)日：2013-05-16

    申请号：US13297101

    申请日：2011-11-15

    申请人： Nirwan Ansari ,  Yan Zhang

    发明人： Nirwan Ansari ,  Yan Zhang

    IPC分类号： G06F15/16

    CPC分类号： H04L47/263 ,  H04L47/30 ,  Y02D50/10

    摘要： Technologies are generally described for an enhanced Quantized Congestion Notification (QCN) congestion control approach, referred to as Fair QCN (FQCN) for enhancing fairness of multiple flows sharing link capacity in a high bandwidth, low latency data center network. QCN messages may be fed back to flow sources (e.g., servers) which send packets with a sending rate over their share of the bottleneck link capacity. By enabling the flow sources to regulate their data traffic based on the QCN messages from a congestion control component, the queue length at the bottleneck link may converge to an equilibrium queue length rapidly and TCP throughput performance may be enhanced substantially in a TCP incast circumstance.

    摘要翻译： 技术通常被描述用于增强的量化拥塞通知（QCN）拥塞控制方法，称为公平QCN（FQCN），用于增强在高带宽，低延迟数据中心网络中共享链路容量的多个流的公平性。 QCN消息可以被反馈到以发送速率超过其瓶颈链路容量的份额发送分组的流源（例如，服务器）。 通过使流量源能够根据来自拥塞控制组件的QCN消息来调节其数据流量，瓶颈链路上的队列长度可以快速收敛到平衡队列长度，并且TCP吞吐量性能可能在TCP恶劣情况下显着提高。

    System and Method for Transmission Control Protocol Slow-Start
    3.
    发明申请
    System and Method for Transmission Control Protocol Slow-Start 有权
    传输控制协议慢启动的系统和方法

    公开(公告)号：US20130044598A1

    公开(公告)日：2013-02-21

    申请号：US13340354

    申请日：2011-12-29

    申请人： Yan Zhang ,  Nirwan Ansari ,  Mingquan Wu ,  Hong Heather Yu

    发明人： Yan Zhang ,  Nirwan Ansari ,  Mingquan Wu ,  Hong Heather Yu

    IPC分类号： H04L12/26 ,  H04L12/24

    CPC分类号： H04L43/0882 ,  H04L43/16 ,  H04L47/193 ,  H04L47/27 ,  H04L47/283 ,  H04L47/29

    摘要： An embodiment of a system and method that uses inline measurements to probe available bandwidth for a transmission control protocol, and adaptively sets a slow-start threshold according to the available bandwidth. The method includes initializing a congestion window “cwnd,” sending cwnd packets, estimating an available bandwidth for the cwnd packets. The congestion window cwnd is set to a higher number, and the higher number of further packets is sent if the available bandwidth is greater than a first threshold level. The available bandwidth is re-estimated for the higher number of the further packets, and a soft start threshold “ssthresh” is set to the re-estimated available bandwidth. A statistical measure is calculated for the re-estimated available bandwidth, and the congestion window cwnd is set equal to ssthresh if a ratio of the statistical measure to the re-estimated available bandwidth is less than a second threshold level.

    摘要翻译： 使用在线测量来探测传输控制协议的可用带宽的系统和方法的实施例，并且根据可用带宽自适应地设置慢启动阈值。 该方法包括初始化拥塞窗口cwnd，发送cwnd分组，估计cwnd分组的可用带宽。 拥塞窗口cwnd被设置为更高的数量，并且如果可用带宽大于第一阈值水平，则发送更多数量的另外的分组。 对于更多数量的其他分组重新估计可用带宽，并且将软启动阈值ssthresh设置为重新估计的可用带宽。 对于重新估计的可用带宽计算统计度量，并且如果统计度量与重新估计的可用带宽的比率小于第二阈值水平，则将拥塞窗口cwnd设置为等于ssthresh。

    Fair quantized congestion notification (FQCN) to mitigate transport control protocol (TCP) throughput collapse in data center networks
    4.
    发明授权
    Fair quantized congestion notification (FQCN) to mitigate transport control protocol (TCP) throughput collapse in data center networks 有权
    公平的量化拥塞通知（FQCN），以缓解数据中心网络中的传输控制协议（TCP）吞吐量崩溃

    公开(公告)号：US09237107B2

    公开(公告)日：2016-01-12

    申请号：US13297101

    申请日：2011-11-15

    申请人： Nirwan Ansari ,  Yan Zhang

    发明人： Nirwan Ansari ,  Yan Zhang

    IPC分类号： G06F15/16 ,  H04L12/825 ,  H04L12/835

    CPC分类号： H04L47/263 ,  H04L47/30 ,  Y02D50/10

    摘要： Technologies are generally described for an enhanced Quantized Congestion Notification (QCN) congestion control approach, referred to as Fair QCN (FQCN) for enhancing fairness of multiple flows sharing link capacity in a high bandwidth, low latency data center network. QCN messages may be fed back to flow sources (e.g., servers) which send packets with a sending rate over their share of the bottleneck link capacity. By enabling the flow sources to regulate their data traffic based on the QCN messages from a congestion control component, the queue length at the bottleneck link may converge to an equilibrium queue length rapidly and TCP throughput performance may be enhanced substantially in a TCP incast circumstance.

    摘要翻译： 技术通常被描述用于增强的量化拥塞通知（QCN）拥塞控制方法，称为公平QCN（FQCN），用于增强在高带宽，低延迟数据中心网络中共享链路容量的多个流的公平性。 QCN消息可以被反馈到以发送速率超过其瓶颈链路容量的份额发送分组的流源（例如，服务器）。 通过使流量源能够根据来自拥塞控制组件的QCN消息来调节其数据流量，瓶颈链路上的队列长度可以快速收敛到平衡队列长度，并且TCP吞吐量性能可能在TCP恶劣情况下显着提高。

    System and method for transmission control protocol slow-start
    5.
    发明授权
    System and method for transmission control protocol slow-start 有权
    传输控制协议的启动系统和方法

    公开(公告)号：US09178789B2

    公开(公告)日：2015-11-03

    申请号：US13340354

    申请日：2011-12-29

    申请人： Yan Zhang ,  Nirwan Ansari ,  Mingquan Wu ,  Hong Heather Yu

    发明人： Yan Zhang ,  Nirwan Ansari ,  Mingquan Wu ,  Hong Heather Yu

    IPC分类号： G01R31/08 ,  H04L12/26 ,  H04L12/807 ,  H04L12/801 ,  H04L12/841

    CPC分类号： H04L43/0882 ,  H04L43/16 ,  H04L47/193 ,  H04L47/27 ,  H04L47/283 ,  H04L47/29

    摘要： An embodiment of a system and method that uses inline measurements to probe available bandwidth for a transmission control protocol, and adaptively sets a slow-start threshold according to the available bandwidth. The method includes initializing a congestion window “cwnd,” sending cwnd packets, estimating an available bandwidth for the cwnd packets. The congestion window cwnd is set to a higher number, and the higher number of further packets is sent if the available bandwidth is greater than a first threshold level. The available bandwidth is re-estimated for the higher number of the further packets, and a soft start threshold “ssthresh” is set to the re-estimated available bandwidth. A statistical measure is calculated for the re-estimated available bandwidth, and the congestion window cwnd is set equal to ssthresh if a ratio of the statistical measure to the re-estimated available bandwidth is less than a second threshold level.

    摘要翻译： 使用在线测量来探测传输控制协议的可用带宽的系统和方法的实施例，并且根据可用带宽自适应地设置慢启动阈值。 该方法包括初始化拥塞窗口“cwnd”，发送cwnd数据包，估计cwnd数据包的可用带宽。 拥塞窗口cwnd被设置为更高的数量，并且如果可用带宽大于第一阈值水平，则发送更多数量的另外的分组。 对于更多数量的另外的分组重新估计可用带宽，并且将软启动阈值“ssthresh”设置为重新估计的可用带宽。 对于重新估计的可用带宽计算统计度量，并且如果统计度量与重新估计的可用带宽的比率小于第二阈值水平，则将拥塞窗口cwnd设置为等于ssthresh。

    Hierarchical energy optimization for datacenter networks
    6.
    发明授权
    Hierarchical energy optimization for datacenter networks 有权
    数据中心网络的分层能量优化

    公开(公告)号：US08700928B2

    公开(公告)日：2014-04-15

    申请号：US13819267

    申请日：2012-05-21

    申请人： Nirwan Ansari ,  Yan Zhang

    发明人： Nirwan Ansari ,  Yan Zhang

    IPC分类号： G06F1/00 ,  G06F1/26 ,  G06F1/32 ,  G06F15/173 ,  H04L12/28

    CPC分类号： G06F1/32 ,  G06F1/26 ,  G06F1/3203 ,  G06F1/3278 ,  G06F1/3287 ,  Y02D10/157 ,  Y02D10/171

    摘要： Technologies are presented for power optimization of datacenter networks in a hierarchical perspective. In some examples, a two-level power optimization model may be established to reduce the power consumption of datacenter networks by switching off network switches and links while still guaranteeing full connectivity and maximum link utilization. The model may be implemented by solving a capacitated constraint multi-commodity flow (CMCF) problem employing simple heuristic techniques. A power status of network switches may be determined according to a network traffic matrix and the CMCF optimization determined at core-level and at pod-level. A complementary process to provision whole network connectivity and to meet quality of service (QoS) goals may also be performed.

    摘要翻译： 针对数据中心网络的功能优化技术进行了分层分析。 在一些示例中，可以建立两级功率优化模型，以通过关闭网络交换机和链路来减少数据中心网络的功耗，同时仍然保证完全连接和最大链路利用率。 该模型可以通过使用简单的启发式技术来求解容许约束多商品流（CMCF）问题来实现。 网络交换机的电源状态可以根据网络流量矩阵确定，CMCF优化在核心级别和pod级确定。 也可以执行提供整个网络连接和满足服务质量（QoS）目标的补充过程。

    Battery case
    7.
    外观设计
    Battery case 有权

    公开(公告)号：USD850373S1

    公开(公告)日：2019-06-04

    申请号：US29675883

    申请日：2019-01-07

    申请人： Yan Zhang

    设计人： Yan Zhang

    Intelligent Pipeline Small Leaks and Thefts Detection Methods and Systems
    8.
    发明申请
    Intelligent Pipeline Small Leaks and Thefts Detection Methods and Systems 审中-公开

    公开(公告)号：US20180246004A1

    公开(公告)日：2018-08-30

    申请号：US15443658

    申请日：2017-02-27

    申请人： Yan Zhang

    发明人： Yan Zhang

    IPC分类号： G01M3/24 ,  G01M3/28

    CPC分类号： G01M3/243 ,  G01M3/2815

    摘要： Four (4) methods and systems that utilize these methods are claimed in the present invention for intelligently detecting pipeline small leaks, thefts, and their details.In the Energy Flow Line Method, the measured flow data at both ends of the pipeline will be monitored and analyzed. If flow changes that meet the criteria are identified, a leak or a theft is detected. The energy wave front speed is introduced and the unsteady flow mathematical model of the subject pipeline is utilized to calculate leak details.In the Filtered Pressure Waves Method, the measured pressure data at both ends of the pipeline will be monitored and analyzed. After filtering, only those pressure waves that are not originated at the ends of the pipeline will be selected as candidates. For each computation step, consecutively apply the 2 travelling time windows template 1 and template 2 to those candidates, and process those candidates within each window. Leaks, thefts and their details (except for leaked amount) can be obtained if the detected leak locations meet the criteria, even when the fluid is stagnant for some time.The Enhanced Filtered Pressure Waves Method, as the name suggests, is the enhanced version of the Filtered Pressure Waves Method if the fluid is not stagnant for some time. The essential part of the Energy Flow Line Method is used to extend the function not only to provide the leaked amount, but also to verify the leak and the leak location in order to avoid sending false alarms. The measured flow data at the outlet end of the pipeline is also monitored and the unsteady flow mathematical model of the subject pipeline is utilized. If the fluid is stagnant for some time, the leaked amount will be calculated without measured data to be compared. The estimated leak location will be provided with a search range.In the Mutual Confirmation Method, essential parts of the above 3 methods are utilized to extend the capability and to confirm each finding. If any result that contradicts the solution is identified, find a new one that fits. By providing the solution that is mutually confirmed with 2 sets of leak details, sending false alarms can be avoided. This method is particularly developed to solve some issues in the real time monitoring applications, especially in SCADA environments, to have shorter calculation time. The unsteady flow mathematical model of the subject pipeline is indispensable for this method. If the fluid is stagnant for some time, the leaked amount will be calculated without measured data to be compared. Also the estimated leak location will be provided with a search range.The present invention is suitable for most pipeline applications, including very long pipelines (for instance, over 200 km), existing pipelines (with min or no modification on existing sensor groups), and pipelines that are shut for some time (excluding using the Energy Flow Line Method), and easily used as a cross checking tool to other pipelines and other online leak detection systems. The fluids in pipelines can be gases, liquids, and multi-phase fluids.