公开(公告)号：US20150195136A1

公开(公告)日：2015-07-09

申请号：US14164876

申请日：2014-01-27

Applicant: Cisco Technology, Inc.

Inventor： Grégory Mermoud ,  Jean-Philippe Vasseur ,  Sukrit Dasgupta

IPC: H04L12/24 ,  G06N99/00 ,  H04L12/26

CPC classification number: H04L41/5025 ,  G06N99/00 ,  G06N99/005 ,  H04L41/12 ,  H04L43/0852 ,  H04L45/02 ,  H04L45/70 ,  H04L47/122 ,  H04L47/365 ,  H04W24/02 ,  H04W24/04 ,  Y04S40/164

Abstract: In one embodiment, a predictive model is constructed by mapping multiple network characteristics to multiple network performance metrics. Then, a network performance metric pertaining to a node in a network is predicted based on the constructed predictive model and one or more network characteristics relevant to the node. Also, a local parameter of the node is optimized based on the predicted network performance metric.

Abstract translation: 在一个实施例中，通过将多个网络特性映射到多个网络性能度量来构建预测模型。 然后，基于所构建的预测模型和与节点相关的一个或多个网络特性来预测与网络中的节点有关的网络性能度量。 此外，基于预测的网络性能度量来优化节点的本地参数。

公开(公告)号：US20150193694A1

公开(公告)日：2015-07-09

申请号：US14164446

申请日：2014-01-27

Applicant: Cisco Technology, Inc.

Inventor： Jean-Philippe Vasseur ,  Javier Cruz Mota ,  Andrea Di Pietro

IPC: G06N99/00 ,  H04L12/26 ,  G06N3/08 ,  H04L29/06

CPC classification number: G06N99/005 ,  G06N3/0454 ,  G06N3/08 ,  G06N3/084 ,  H04L41/142 ,  H04L41/16 ,  H04L43/10 ,  H04L63/14 ,  H04L63/1408 ,  H04L63/1416

Abstract: In one embodiment, a first data set is received by a network device that is indicative of the statuses of a plurality of network devices when a type of network attack is not present. A second data set is also received that is indicative of the statuses of the plurality of network devices when the type of network attack is present. At least one of the plurality simulates the type of network attack by operating as an attacking node. A machine learning model is trained using the first and second data set to identify the type of network attack. A real network attack is then identified using the trained machine learning model.

Abstract translation: 在一个实施例中，当网络攻击的类型不存在时，第一数据集由网络设备接收，其指示多个网络设备的状态。 还接收当存在网络攻击的类型时指示多个网络设备的状态的第二数据集。 多个中的至少一个通过作为攻击节点操作来模拟网络攻击的类型。 使用第一和第二数据集来训练机器学习模型以识别网络攻击的类型。 然后使用训练有素的机器学习模型识别真实的网络攻击。

公开(公告)号：US20150186799A1

公开(公告)日：2015-07-02

申请号：US14165462

申请日：2014-01-27

Applicant: CISCO TECHNOLOGY, INC.

Inventor： Sukrit Dasgupta ,  Jean-Philippe Vasseur ,  Grégory Mermoud

IPC: G06N99/00

CPC classification number: G06N99/005

Abstract: In one embodiment, techniques are shown and described relating to a point-to-multipoint communication infrastructure for expert-based knowledge feed-back using learning machines. A learning machine may communicate an expert discovery request into a network to discover one or more experts, and then receive from the one or more experts, one or more expert discovery responses. Based on the one or more received expert discovery responses, the learning machine may then build a dynamic multicast tree of experts to assist the learning machine in a computer network.

Abstract translation: 在一个实施例中，与使用学习机器的基于专家的知识反馈的点对多点通信基础设施相关的技术被示出和描述。 学习机器可以将专家发现请求传达到网络中以发现一个或多个专家，然后从一个或多个专家接收一个或多个专家发现响应。 基于一个或多个接收到的专家发现响应，学习机器然后可以构建专家的动态多播树，以帮助学习机器在计算机网络中。

公开(公告)号：US20150186798A1

公开(公告)日：2015-07-02

申请号：US14163638

申请日：2014-01-24

Applicant: CISCO TECHNOLOGY, INC.

Inventor： Jean-Philippe Vasseur ,  Grégory Mermoud ,  Sukrit Dasgupta

IPC: G06N99/00

CPC classification number: G06N99/005 ,  G06Q10/0631 ,  G06Q10/06375 ,  H04L12/185 ,  H04L41/145 ,  H04L41/147 ,  H04L41/16 ,  H04L45/48 ,  H04L47/2483 ,  H04L67/26

Abstract: In one embodiment, a learning data processor determines a plurality of machine learning features in a computer network to collect. Upon receiving data corresponding to the plurality of features, the learning data processor may aggregate the data, and pushes the aggregated data for select features to interested learning machines associated with the computer network.

Abstract translation: 在一个实施例中，学习数据处理器确定要收集的计算机网络中的多个机器学习特征。 在接收到与多个特征相对应的数据时，学习数据处理器可以聚合数据，并将用于选择特征的聚合数据推送到与计算机网络相关联的感兴趣的学习机器。

公开(公告)号：US20150110159A1

公开(公告)日：2015-04-23

申请号：US14579375

申请日：2014-12-22

Applicant: Cisco Technology, Inc.

Inventor： Jonathan W. Hui ,  Jean-Philippe Vasseur

IPC: H04B1/713

CPC classification number: H04B1/713 ,  H04B1/7143 ,  H04L45/14 ,  H04L45/16 ,  H04L45/18 ,  H04W40/14 ,  H04W40/246 ,  H04W48/18

Abstract: In one embodiment, a device in a channel hopping, communication network independently maintains a slot counter, and computes a channel identification (ID) based on a function having inputs of a unique feature of the device, ii) a current slot of the slot counter, and iii) a set of possible channel IDs. Accordingly, the device configures its radio to receive on the computed channel ID for the respective current slot. In another embodiment, the device may determine, for a neighbor device, a current neighbor slot and unique neighbor feature, and correspondingly computes a neighbor channel ID based on the function using the unique neighbor feature, the current neighbor slot, and the set of a possible channel IDs. As such, the device configures its radio to transmit on the computed neighbor channel ID for the respective current neighbor slot.

Abstract translation: 在一个实施例中，信道跳跃，通信网络中的设备独立地维护时隙计数器，并且基于具有设备的唯一特征的输入的功能来计算信道标识（ID），ii）时隙计数器的当前时隙 ，以及iii）一组可能的频道ID。 因此，设备将其无线电配置为针对相应的当前时隙的所计算的信道ID进行接收。 在另一个实施例中，设备可以为邻居设备确定当前相邻时隙和唯一邻居特征，并且基于使用唯一邻居特征，当前相邻时隙和所述一组的相应功能来相应地计算邻居信道ID 可能的频道ID。 因此，设备将其无线电配置为针对相应的当前相邻时隙的所计算的邻居信道ID进行发送。

公开(公告)号：US20150092538A1

公开(公告)日：2015-04-02

申请号：US14039191

申请日：2013-09-27

Applicant: Cisco Technology, Inc.

Inventor： Jean-Philippe Vasseur ,  Sukrit Dasgupta ,  Grégory Mermoud

IPC: H04L12/24 ,  H04L12/26

CPC classification number: H04L45/24 ,  H04L43/08 ,  H04L45/308

Abstract: In one embodiment, a plurality of communication paths in a second direction in a communication network is determined, based on reversing communication paths established in a first direction in the communication network. Then, a path quality of the communication paths in the second direction is monitored. Based on the monitored path quality, it is then determined whether the communication paths in the second direction satisfy a communication requirement. Finally, a particular communication path of unacceptable quality in the second direction is detected when the particular communication path in the second direction fails to satisfy the communication requirement.

Abstract translation: 在一个实施例中，基于在通信网络中沿第一方向建立的反向通信路径来确定在通信网络中的第二方向上的多个通信路径。 然后，监视第二方向上的通信路径的路径质量。 基于所监视的路径质量，确定第二方向的通信路径是否满足通信要求。 最后，当第二方向上的特定通信路径不能满足通信要求时，检测到在第二方向上具有不可接受质量的特定通信路径。

公开(公告)号：US08984277B2

公开(公告)日：2015-03-17

申请号：US13631106

申请日：2012-09-28

Applicant: Cisco Technology, Inc.

Inventor： Sukrit Dasgupta ,  Jean-Philippe Vasseur

IPC: H04L29/06 ,  H04L12/715

CPC classification number: H04L47/2475 ,  H04L45/64 ,  H04L63/062 ,  H04L63/0853 ,  H04L63/0884 ,  H04L67/12

Abstract: In one embodiment, a capable node in a low power and lossy network (LLN) may monitor the authentication time for one or more nodes in the LLN. The capable node may dynamically correlate the authentication time with the location of the one or more nodes in the LLN in order to identify one or more authentication-delayed nodes. The node may then select, based on the location of the one or more authentication-delayed nodes, one or more key-delegation nodes to receive one or more network keys so that the key-delegation nodes may perform localized authentication of one or more of the authentication-delayed nodes. The capable node may then distribute the one or more network keys to the one or more key-delegation nodes.

Abstract translation: 在一个实施例中，低功率和有损网络（LLN）中的能力节点可以监视LLN中的一个或多个节点的认证时间。 能力节点可以将认证时间与LLN中的一个或多个节点的位置动态相关，以便识别一个或多个认证延迟节点。 然后，节点可以基于一个或多个认证延迟的节点的位置来选择一个或多个密钥委派节点来接收一个或多个网络密钥，使得密钥委派节点可以执行一个或多个 认证延迟节点。 有能力的节点可以然后将一个或多个网络密钥分配给一个或多个密钥委派节点。

公开(公告)号：US20150030033A1

公开(公告)日：2015-01-29

申请号：US14474655

申请日：2014-09-02

Applicant: Cisco Technology, Inc.

Inventor： Jean-Philippe Vasseur ,  Shmuel Shaffer ,  Sandeep J. Shetty

IPC: H04L12/717 ,  H04L12/707

CPC classification number: H04L45/42 ,  H04L45/22 ,  H04W40/22 ,  H04W40/246 ,  H04W40/26

Abstract: In one embodiment, a data aggregator discovery (DAD) message may be distributed by an associated data aggregator, the DAD message identifying the initiating data aggregator, and comprising a recorded route taken from the data aggregator to a receiving particular node as well as a total path cost for the particular node to reach a root node of the DAG through the recorded route and via the data aggregator. The receiving particular node determines a path cost increase (PCI) associated with use of the data aggregator based on the total path cost as compared to a DAG-based path cost for the particular node to reach the root node via the DAG. If the PCI is below a configured threshold, the particular node may redirect traffic to the data aggregator as source-routed traffic according to the recorded route. The traffic may then be aggregated by the data aggregator, accordingly.

Abstract translation: 在一个实施例中，数据聚合器发现（DAD）消息可以由相关联的数据聚合器分发，DAD消息标识发起数据聚合器，并且包括从数据聚合器到接收特定节点的记录路由以及总数 特定节点通过记录的路由并经由数据聚合器到达DAG的根节点的路径开销。 与特定节点通过DAG到达根节点的基于DAG的路径开销相比，接收特定节点基于总路径开销来确定与数据聚合器的使用相关联的路径成本增加（PCI）。 如果PCI低于配置的阈值，则特定节点可以根据记录的路由将流量重定向为数据聚合器作为源路由业务。 因此，流量可以由数据聚合器进行聚合。

公开(公告)号：US20150023205A1

公开(公告)日：2015-01-22

申请号：US14038120

申请日：2013-09-26

Applicant: Cisco Technology, Inc.

Inventor： Jean-Philippe Vasseur ,  Pascal Thubert ,  Patrick Wetterwald

IPC: H04L12/751

CPC classification number: H04L45/02 ,  H04L45/42

Abstract: In one embodiment, an agent device discovers a set of path computation elements (PCEs) and corresponding available capabilities and resources, and determines particular capabilities and resources of interest in a particular computer network. Upon building a simplified view of the available capabilities and resources of the set of PCEs based on the particular capabilities and resources of interest, the agent device advertises the simplified view of the available capabilities and resources into the particular computer network.

Abstract translation: 在一个实施例中，代理设备发现一组路径计算元件（PCE）和相应的可用能力和资源，并确定特定计算机网络中感兴趣的特定能力和资源。 在基于感兴趣的特定能力和资源构建PCE集合的可用能力和资源的简化视图后，代理设备将可用能力和资源的简化视图通告给特定的计算机网络。

公开(公告)号：US20150003468A1

公开(公告)日：2015-01-01

申请号：US13930463

申请日：2013-06-28

Applicant: Cisco Technology, Inc.

Inventor： Pascal Thubert ,  Jean-Philippe Vasseur ,  Patrick Wetterwald

IPC: H04J3/22 ,  H04L5/00

CPC classification number: H04J3/22 ,  H04B7/2643 ,  H04L5/0037 ,  H04W52/0216 ,  Y02D70/00 ,  Y02D70/1262 ,  Y02D70/144 ,  Y02D70/22 ,  Y02D70/449

Abstract: Techniques are presented herein for use in a Time Division Multiple Access (TDMA) communication system in which devices send transmissions to each other in time slots during a time frame. A plurality of time slots is allocated for a first device to send traffic to a second device. The first device includes in a transmission during at least one of the plurality of time slots an indicator configured to indicate whether a next time slot in the plurality of time slots is used for traffic from the first device to the second device. Thus, the actual usage of a next time slot in a sequence of a plurality of time slots may be dynamically determined by the transmitting device so that the receiving device(s) need not be in the idle listening mode for the next time slot, thereby saving power.

Abstract translation: 技术在本文中被提供用于时分多址（TDMA）通信系统，其中设备在时间帧期间在时隙中彼此发送传输。 为第一设备分配多个时隙以向第二设备发送业务。 第一设备在多个时隙中的至少一个时隙期间包括在传输中，指示符被配置为指示多个时隙中的下一个时隙是否用于从第一设备到第二设备的业务。 因此，多个时隙的序列中的下一个时隙的实际使用可以由发送设备动态地确定，使得接收设备不需要在下一个时隙处于空闲监听模式，从而 节电。