Patent classifications
H04L12/723
MACHINE-LEARNING OPTIMIZATION FOR COMPUTING NETWORKS
A machine-learning optimization of a plurality of networks is provided. The machine-learning optimization includes interconnecting an online platform providing a machine learning module, a core network of computers deploying novel software, and a plurality of Internet network service providers. The platform collects, via the software, performance data of the Internet networks, which the machine learning module utilizes to enhance performance and reduce the latency therein networks by taking into account thousands of real-time and historic latency and bandwidth metrics. Thereby the software continually selects an optimal path through the plurality of Internet networks.
System and Method for Dataplane-Signaled Packet Capture in a Segment Routing Environment
Presented herein are segment-routing methods and systems that facilitate data plane signaling of a packet as a candidate for capture at various network nodes within a segment routing (SR) network. The signaling occurs in-band, via the data plane—that is, a capture or interrogation signal is embedded within the respective packet that carries a user traffic. The signaling is inserted, preferably when the packet is classified, e.g., at the ingress node of the network, to which subsequent network nodes with the SR network are signaled to capture or further inspect the packet for capture.
Load balancing traffic in a MPLS network
A method and system for managing traffic in a network. For each label switch path of at least two logical switch paths, logical paths are identified. Each label switch path begins at a first provider edge and ends at a second provider edge. Most recent data received from the first provider edge is transmitted to the second provider edge via a selected logical path.
MPLS segment-routing
MPLS segment routing is disclosed. In one embodiment, a first core router generates a first data structure that maps first portcodes to respective identities of first neighbor routers or respective first links, wherein the first portcodes identify respective first ports of the first core router, and wherein the first ports are coupled to the first neighbor routers, respectively, via the first links, respectively. The first core router generates and transmits a first link-state packet, wherein the first link-state packet comprises an identity of the first core router and the first data structure.
Data Processing Method and Apparatus and Network Device
Disclosed are a method and apparatus for processing data and a network device, wherein the method for processing data includes: stripping a label switch path (LSP) label of first data to obtain second data having a first pseudo-wire (PW) label, wherein the first data are data of a first network, and the first PW label is a label of the first network; performing label switch on the second data to obtain third data having a second PW label, wherein the second PW label is a label of a second network; encapsulating the third data according to the second network to obtain fourth data, wherein the fourth data are data of the second network; and sending the fourth data to the second network. Through the abovementioned method, data transmission from the first network to the second network is achieved.
SR APP-SEGMENT INTEGRATION WITH SERVICE FUNCTION CHAINING (SFC) HEADER METADATA
In one embodiment, a device in a network receives a packet that includes one or more forwarding labels and a service function chaining (SFC) header. The device removes the one or more forwarding labels from the packet. The device inserts an indication of the one or more forwarding labels into metadata of the SFC header. The device forwards the packet with the inserted indication of the one or more forwarding labels to a service function.
Path Computation Element Hierarchical Software Defined Network Control
A parent PCE controller comprising a memory comprising instructions executable by a processor and a processor coupled to the memory and configured to execute the instructions. Executing the instructions causes the processor to establish a parent-child relationship with at least a first child PCE controller controlling a first domain and a second child PCE controller controlling a second domain, receive a request to create an E2E tunnel from a source to a destination crossing the first domain and the second domain, compute a shortest path from the source to the destination through the first domain and the second domain, transmit a request message to the first child PCE controller for creating a first tunnel segment of the E2E tunnel through the first domain, and transmit a request message to the second child PCE controller for creating a second tunnel segment of the E2E tunnel through the second domain.
Method for assigning and processing a label in an optical network, optical communication device, and optical communication system
The present invention discloses a method for assigning and processing a label in an optical network. The method includes: learning that a label switched path is required to be established in an optical network; generating a label, in which the label is used for indicating that a first optical channel data unit is multiplexed to a second optical channel data unit; the label includes a tributary slot type indication field that is used for indicating a tributary slot type of the second optical channel data unit, and the label further includes a tributary slot assignment indication field that is used for indicating a tributary slot occupied in the second optical channel data unit into which the first optical channel data unit is multiplexed; and sending the label to a node on the label switched path by a signaling message of GMPLS.
Method, apparatus and system for establishing optical bypass
Provided are a method, an apparatus and a system for establishing an optical bypass. The method includes: a route controller sending an optical bypass establishment request carrying information about an ingress node, an egress node and a required bandwidth to an optical transmission controller; and setting a second flow forwarding entry corresponding to the optical bypass for the ingress node and the egress node and sending the set second flow forwarding entry to the ingress node and the egress node when receiving an establishment success notification sent by the optical transmission controller, the establishment success notification being used for indicating that the optical transmission controller has allocated the optical bypass according to the optical bypass establishment request, set a first flow forwarding entry corresponding the bypass for each optical transmission device in the optical bypass, and sent the set first flow forwarding entry to a corresponding optical transmission device.
Segment Routing in a Multi-Domain Network
The present invention provides a method for enabling Segment Routing in a multi-domain network comprising a client network domain and a server network domain, where the client network domain is a packet network domain and the server network domain is a connected-oriented network domain. The method comprises assigning a network segment identifier to each of one or more potential paths through the server network domain between a pair of overlay network nodes in the client network domain, wherein the one or more potential paths are not pre-configured and the or each network segment identifier is suitable for inclusion in one or more data packets to indicate to at least one of the pair of overlay network nodes a preselected network segment routing for the one or more data packets. The present invention further provides a method for routing data packets in the multi-domain network. The method, in an overlay network node in the client network domain, comprises receiving one or more data packets, and retrieving a network segment identifier included in at least one of the one or more data packets. The method further comprises determining that the network segment identifier indicates that the one or more data packets should be routed over a pre-selected potential path through the server network domain, and, based on the determining, triggering the server network domain to configure the pre-selected potential path through the server network domain.