利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

13 条记录 (耗时 0.012 秒)

    Method and system in a packet switching network for dynamically adjusting the bandwidth of a continuous bit rate virtual path connection according to the network load
    2.
    发明公开
    Method and system in a packet switching network for dynamically adjusting the bandwidth of a continuous bit rate virtual path connection according to the network load 审中-公开
    在分组的方法和系统交换网络来动态调整用连续比特率的虚拟路径的带宽，根据网络负载

    公开(公告)号：EP1001574A1

    公开(公告)日：2000-05-17

    申请号：EP98480078.9

    申请日：1998-11-10

    申请人： International Business Machines Corporation

    发明人： Fichou, Aline ,  Galand, Claude ,  Nicolas, Laurent ,  Basso, Claude

    IPC分类号： H04L12/56 ,  H04Q11/04

    CPC分类号： H04L12/5602 ,  H04L2012/5619 ,  H04L2012/5634 ,  H04Q11/0478

    摘要： The present invention relates to a system and method for dynamically adjusting the bandwidth of a continuous bit rate virtual path connection established between a source node and a destination node within a packet or cell switching network comprising a plurality of nodes interconnected with transmission links. In the network, a bandwidth management server having access to information concerning network nodes and transmission links is defined. This server is informed each time a virtual path connection or a virtual channel connection is established on the network with an indication concerning the initial bandwidth reserved for said connection. The server detects and shares, on a continuous or periodical mode, the bandwidth which is available on transmission links among the bandwidth adjustable continuous bit rate virtual path connections and determines for each connection a new bandwidth. The source node is informed each time a new bandwidth is computed. It adjusts the bandwidth of the corresponding bandwidth adjustable continuous bit rate virtual path connection accordingly.

    摘要翻译： 本发明涉及一种系统和方法，用于动态地调整源节点和一个包或信元交换网络包括与传输链路互连的节点内的多个目的地节点之间建立的连续的比特速率虚拟通路连接的带宽。 在网络中，具有获取信息关于网络节点和传输链路的带宽管理服务器定义。 此服务器的每个虚拟路径连接或虚拟信道连接与上指示关于用于所述连接保留的初始带宽的网络上建立时间通知。 服务器检测和股，在一个连续的或周期性的方式，频带宽度的所有其可在带之间的传输链路宽度可调整的连续比特率虚通道连接和确定性地雷为每个连接一个新的带宽。 每一个新的带宽计算时间源节点被告知。 它相应bestimmt相应带宽可调连续比特率虚拟通路连接的带宽。

    A method and an apparatus for shaping the output traffic in a fixed length cell switching network node
    3.
    发明公开
    A method and an apparatus for shaping the output traffic in a fixed length cell switching network node 失效
    方法和装置用于成形输出流量在网络节点为固定长度单元的Vermittung

    公开(公告)号：EP0702473A1

    公开(公告)日：1996-03-20

    申请号：EP94480087.9

    申请日：1994-09-19

    申请人： International Business Machines Corporation

    发明人： Fichou, Aline ,  Galand, Claude ,  Foriel, Pierre-André

    IPC分类号： H04L12/56 ,  H04Q11/04

    CPC分类号： H04L49/505 ,  H04L12/5602 ,  H04L49/30 ,  H04L49/503 ,  H04L2012/5615 ,  H04L2012/5616 ,  H04L2012/5619 ,  H04L2012/5632 ,  H04L2012/5636 ,  H04L2012/5649 ,  H04L2012/5679 ,  H04L2012/568

    摘要： An method and an apparatus implementing a shaping function in a fixed length cell switching network node (5) adapter supporting output lines (25); the invention uses a Time Division Multiplexing (TDM) table (270) where each entry is a pointer to a the first cell of a queue (240) of cells of a given traffic; When a new traffic is established, the TDM table is updated; placement device (250) performs the pre-computation of the best placement of the entries reserved for one traffic in the TDM table (270) minimizing the Cell Delay Variation as computed by the GCRA policer (ITU standard organization). The Cell Delay Variation (CDV) defined as the deviation of the placement of the cells in the output stream from their ideal position which is when the entries are spaced with an interval corresponding to the period of traffic negociated at traffic establishment time. The preferred embodiments includes a scheduler (280) able to read the TDM table and to fetch the corresponding cell in the storage (230) to send it onto the output line via the line interface adapter.

    摘要翻译： 的方法和在一个固定长度的信元交换网络节点（5）执行一个整形函数支撑适配器输出线的装置（25）; 本发明使用时分复用（TDM）表（270），其中每个条目是一个指向一个给定的业务的小区的队列（240）的所述第一小区; 当建立一个新的业务，则TDM表被更新; 放置装置（250）执行对在最大限度地减少信元延迟变化由GCRA策略器（ITU标准组织），为计算出的TDM表（270）一个业务保留的项的最佳位置的预先计算。 定义为在输出流中的细胞的位置从它们的理想位置的所有的偏差是当条目与在间隔对应于交通建立时间协商的信业务的周期间隔信元延迟变化（CDV）。 优选实施例包括调度器（280）能够读取TDM表并获取在存储（230）对应的小区发送它放到经由线路接口适配器的输出线。

    Connections bandwidth right sizing based on network resources occupancy monitoring
    4.
    发明公开
    Connections bandwidth right sizing based on network resources occupancy monitoring 有权
    基于网络的资源的分配的观察链路带宽的校正

    公开(公告)号：EP1069801A1

    公开(公告)日：2001-01-17

    申请号：EP99480063.9

    申请日：1999-07-13

    申请人： International Business Machines Corporation

    发明人： Fichou, Aline ,  Le Pennec, Jean-François ,  Galand, Claude

    IPC分类号： H04Q11/04 ,  H04L12/56

    CPC分类号： H04Q11/0478 ,  H04L41/0896 ,  H04L41/5003 ,  H04L41/5009 ,  H04L41/5035 ,  H04L47/10 ,  H04L47/11 ,  H04L47/15 ,  H04L47/70 ,  H04L47/745 ,  H04L47/762 ,  H04L47/822 ,  H04L47/826 ,  H04L2012/5632 ,  H04L2012/5636 ,  H04L2012/5647 ,  H04L2012/5682

    摘要： Disclosed herein is a connection bandwidth management process and system for use in a high speed packet switching network. The network comprises a plurality of switching nodes interconnected through a plurality of communication links. Each of the switching nodes comprises means for switching packets from at least one input link to at least one output link. Each of the output links are coupled to at least one buffer in the switching node for queuing packets before they are transmitted over the output link. Each of the communication links supports the traffic of a plurality of user connections statistically multiplexed over the link. Each user connection is allocated an initial agreed-upon bandwidth through the network, with each of the communication links being possibly oversubscribed.
    The connection bandwidth management process according to the invention comprises the steps of:
    Link monitoring data on the communication links are periodically received in a network monitoring center, and stored in a computer memory in the network monitoring center. Then, one monitored link is selected and the corresponding link monitoring data are retrieved from the computer memory. The link monitored data retrieved for the selected link is analyzed, and it is determined whether the selected link is oversubscribed or not. If it is determined that the selected link is oversubscribed and that the link monitoring data for the selected link satisfies at least one predetermined condition the bandwidth initially allocated to each of the connections boarded on the selected link is reallocated, such that, the sum of the reallocated bandwidth of the connections boarded on the selected link is less or equal to the total bandwidth capacity of the selected link.
    The process recycles until all the monitored links have been selected.

    Network capacity planning based on buffers occupancy monitoring
    5.
    发明公开
    Network capacity planning based on buffers occupancy monitoring 有权
    网络容量监测缓冲器的占有率为基础的规划

    公开(公告)号：EP1069729A1

    公开(公告)日：2001-01-17

    申请号：EP99480062.1

    申请日：1999-07-13

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Fichou, Aline ,  Le Pennec, Jean-Francois ,  Galand, Claude

    IPC分类号： H04L12/24 ,  H04Q11/04

    CPC分类号： H04L43/0882 ,  H04L41/0896 ,  H04L43/0829 ,  H04L43/0852 ,  H04L43/0858 ,  H04L43/087 ,  H04L43/16 ,  H04L2012/5623 ,  H04L2012/5626 ,  H04L2012/5681 ,  H04Q11/0478

    摘要： Disclosed herein is a method and a system of network capacity planning for use in a high speed packet switching network. The network comprises a plurality of switching nodes interconnected through a plurality of communication links, each of the switching nodes comprises means for switching packets from at least one input link to at least one output link. Each of the output links is coupled to at least one buffer in the switching node for queuing packets before they are transmitted over the output link. The network capacity planning method of the invention comprises the following steps:
    In each of the switching nodes and for each of the output links, a time distribution of the occupancy of each buffer during a predetermined monitoring time period is measured, and stored in a centralized memory location. Then, the buffer occupancy time distribution data are retrieved from the centralized memory location in all the switching nodes, gathered and stored in a network dedicated server. These buffer occupancy time distribution data for all the nodes are transmitted from the dedicated network server to a network monitoring center. In the network monitoring center, the buffer occupancy time distribution data are integrated on a larger time scale, and stored. Finally, the integrated buffer occupancy time distribution data are used to apply network capacity planning actions to the network resources.

    摘要翻译： 公开的是在一个方法和网络容量规划用于在高速分组交换网络中使用的系统。 该网络包括切换通过通信链路互连的多个节点复数，每个开关的节点的装置包括用于从至少一个输入连杆交换分组到至少一个输出链路。 每个输出链路被耦合到至少一个缓冲器在交换节点为它们之前超过输出连杆反mitted排队的数据包。 本发明的网络容量规划方法，包括如下步骤：在每个交换节点和对于每个输出链路，在预定的监视时间段的每个缓冲器的占用的时间分布进行测量，并存储在一个集中 内存位置。 然后，缓冲器占用时间分布数据从集中存储位置中的所有交换节点的检索，在一个网络专用服务器收集和存储。 对所有节点这些缓冲器占用时间分布数据是从专用网络服务器到网络监控中心反mitted。 在网络监控中心，缓冲器占用时间分布数据被集成在一个更大的时间尺度，并存储。 最后，集成缓存占用时间分布数据用于应用网络容量规划行动，以网络资源。

    Access control system for a shared buffer
    6.
    发明公开
    Access control system for a shared buffer 失效
    Zugriffsteuerungssystem eines gemeinsamen Pufferspeichers

    公开(公告)号：EP0748087A1

    公开(公告)日：1996-12-11

    申请号：EP95480070.2

    申请日：1995-06-09

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Galand, Claude ,  Austruy, Pierre ,  Fichou, Aline ,  Iliadis, Ilias

    IPC分类号： H04L12/56

    CPC分类号： H04L47/10 ,  H04L47/29 ,  H04L49/103 ,  H04L49/205 ,  H04L49/3027

    摘要： An improved access control system for a common or global data storage supporting virtual output queues dedicated to each of the output lines of the storage is described for data of different priorities. The improvement consisting in having thresholds for each priority class with respect to the global occupation level of the storage and to the occupation level of each virtual queue. The new access control system enables a contention control. It further includes the generation of a backpressure signal for the data transmitting input as to indicate the success of the transmission. This signal can be reduced to a single bit irrespective of the number of thresholds and priority classes.

    摘要翻译： 针对不同优先级的数据描述了用于支持专用于存储器的每个输出线的虚拟输出队列的公共或全局数据存储器的改进的访问控制系统。 该改进包括相对于每个虚拟队列的存储的全局占用级别和占用级别的每个优先级类别具有阈值。 新的访问控制系统实现了争用控制。 它还包括产生用于数据发送输入的背压信号以指示传输的成功。 该信号可以减少到单个位，而不管阈值和优先级的数量。

    Method and system for optimizing the end to end path selection in very large packet switching networks
    8.
    发明公开
    Method and system for optimizing the end to end path selection in very large packet switching networks 审中-公开
    方法和系统，用于在非常大的分组交换网络优化端至端的路径选择

    公开(公告)号：EP1009131A1

    公开(公告)日：2000-06-14

    申请号：EP98480090.4

    申请日：1998-12-11

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Brun, Gérard ,  Chobert, Jean-Paul ,  Boudeile, Guy ,  Fichou, Aline ,  Galand, Claude

    IPC分类号： H04L12/56

    CPC分类号： H04L45/04 ,  H04L45/46 ,  H04L2012/562 ,  H04L2012/5621 ,  H04L2012/5687

    摘要： The present invention relates to a method and system for optimizing the end to end path selection in very large packet switching networks.The network is divided in a backbone subnetwork and a plurality of access subnetworks. These subnetworks have a certain hierarchy, but direct links between access subnetworks are allowed. To fulfil the path request between nodes not pertaining to the same subnetwork, the path selection is performed in the backbone subnetwork by concatenating the backbone subnetwork topology with the access subnetwork topologies where the source or destination nodes are located. Only the required subset within access subnetwork topologies is transferred and cached into the backbone subnetwork topology. The main advantages are that :

    The path is computed in one step only
    There is no retry because there is no summarization.
    The computation is faster because applied on a subset of the overall topology (the backbone subnetwork plus at most two access subnetworks).

    摘要翻译： 本发明涉及一种用于在非常大的分组交换网络networks.The优化端至端路径选择被分成骨架子网与接入子网的多个方法和系统。 这些子网有一定的层次，但接入子网之间的直接联系是允许的。 为了满足不属于相同的子网络节点之间的请求路径，路径选择是在主链中的子网络通过连接与所述接入子网拓扑，其中源节点或目的地节点位于骨干子网拓扑进行。 只有接入子网的拓扑结构中所需要的子集，转移和高速缓存到骨干子网的拓扑结构。 的主要优点是：路径计算在一个步骤中仅没有重试因为没有总结。 计算速度更快，因为对整体拓扑结构（主干子网加最多两个接入子网）的一个子集应用。

    Distributed directory services for locating network resources in a very large packet switching network
    9.
    发明公开
    Distributed directory services for locating network resources in a very large packet switching network 审中-公开
    在一个非常大的分组交换网络中定位网络资源的分布式目录服务

    公开(公告)号：EP1009130A1

    公开(公告)日：2000-06-14

    申请号：EP98480089.6

    申请日：1998-12-11

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Brun, Gérard ,  Chobert, Jean-Paul ,  Boudeile, Guy ,  Fichou, Aline ,  Galand, Claude

    IPC分类号： H04L12/56

    CPC分类号： H04L45/04 ,  H04L45/46 ,  H04L2012/562 ,  H04L2012/5621 ,  H04L2012/5687

    摘要： The present invention relates to a method and system of locating a network resource in a packet switching network divided in a backbone subnetwork connected to one or a plurality of access subnetworks. The access subnetworks comprise one or a plurality of access border nodes directly connected to the backbone subnetwork. The backbone subnetwork comprises one or a plurality of backbone border nodes directly connected to the access subnetworks. Border nodes of different subnetworks are connected by border links.
    The method in access border nodes involves the steps of :

    receiving a query message comprising a resource name, the resource name including a prefix;
    comparing the resource name prefix with the prefixes stored in an access border node directory database, said access border node directory database comprising prefixes of the resources local to the access border node subnetwork;
    determining whether the resource name relates to a resource which is local to the access border node subnetwork or not;
    forwarding said query message to an adjacent backbone border node when the resource name relates to a resource which is not local to the access border node subnetwork.

    The method in backbone border nodes involves the steps of :

    receiving a query message comprising a resource name, the resource name including a prefix;
    comparing the resource name prefix with the prefixes stored in one or a plurality of backbone border node directory databases. Each backbone border node directory database corresponds to an access subnetwork managed by the backbone border node;
    determining whether the resource name relates to a resource which belongs to an access subnetwork that the backbone border node manages or not;
    forwarding the query message to an adjacent access border node when the resource name relates to a resource which belongs to an access border node subnetwork managed by the backbone border.

    Each access subnetwork has its own spanning tree and distributed topology, and interactions between access networks are limited to a minimum. The size of distributed topologies is kept small and the control traffic is mostly limited to subnetworks.

    摘要翻译： 本发明涉及定位在分组交换网络划分成连接到一个或接入子网的多个骨干子网的网络资源的方法和系统。 访问子网包括一个或接入边界的多个节点直接连接到主干网子网。 骨干子网包含一个或骨干边境的多个节点直接连接到接入子网。 不同子网的边界节点通过边界左连接。 在接入节点边界的方法，包括以下步骤：接收查询消息包括资源名称，资源名称包括前缀; 比较资源名称前缀与存储在访问边界节点目录数据库的前缀，所述接入边界节点目录数据库，包括资源的前缀本地接入节点边界子网; 确定性矿山资源是否名涉及资源全部是本地的接入节点子网边界或没有; 说在邻近骨架边界节点转发查询消息当资源名称涉及资源全部是不是本地的接入边界节点子网。 在骨干节点边框的方法包括以下步骤：接收查询消息包括资源名称，资源名称包括前缀; 比较资源名称前缀存储在一个前缀或骨干边界节点目录数据库的多元性。 每个骨干边界节点目录数据库对应于由骨干边界节点管理接入子网; 确定性矿山资源是否名涉及属于接入子网做的骨干边界节点管理或不是资源; 在相邻接入边界节点转发查询消息当资源名称涉及属于能够访问由骨干边境管理边界节点子网的资源。 每个接入子网都有自己的生成树拓扑结构和分布，以及接入网络之间的交互限制到最小。 分布式拓扑的尺寸保持较小和控制业务大多​​局限于子网。