Fujitsu Corporation

Ching-Fong Su

Takeo Hamada

Richard R Rabbat

Hung-ying Tyan

Wei-Peng Chen

Takafumi Chujo

Chenxi Zhu

Jonathan Russell Agre

Tomohiko Taniguchi

Cechan Tian

Alexei L Glebov

Kaoru Chujo

Yao-Min Chen

Peter J Czezowski

Xiangying Yang

Multicast transmission in an optical network includes receiving a primary token at a root node of the optical network authorizing the point-to-multipoint data transmission from the root node to a plurality of branch nodes of the optical network. It is determined whether the root node comprises a virtual output queue associated specifically with the branch nodes included on the point-to-multipoint transmission. The virtual output queue is created that is associated specifically with the branch nodes included in the point-to-multipoint transmission if it is determined the root node does not comprise such a queue. The data is placed in the virtual output queue for transmission to the branch nodes. A control message is transmitted to each branch node identifying the point-to-multipoint data transmission, and the control message facilitates creation of a virtual output queue at the branch nodes associated specifically with any other branch nodes that are to receive the data transmission via the branch node at which the virtual output queue is created. The data is transmitted to a first one of the branch nodes.

Multicast transmissions in optical burst transport

A network includes multiple nodes interconnected to form a ring topology. These nodes support data transmissions over the network using tokens. To send and receive data over the network, nodes may process control messages. A node can receive a token authorizing transmission on one of multiple data channels, determine a transmission allocation, which represents an amount of time that the authorized data channel may be utilized to transmit data, and determine a destination allocation, which represents a proportion of the transmission allocation that may be utilized to transmit the data to a particular destination. The node can also transmit the data on the authorized data channel in accordance with the transmission allocation and the destination allocation.

Scheduling token-controlled data transmissions in communication networks

A method for reusing wireless resources in a wireless network, includes determining the probability of a first communication with a first relay station experiencing interference from a second relay station. The method also includes, upon determining that the probability of experiencing interference from the second relay station is greater than an interference threshold: allocating a first wireless resource to the first relay station and the second relay station; designating the first wireless resource as a primary wireless resource for the first relay station; designating the first wireless resource as a secondary wireless resource for the second relay station; allocating a second wireless resource to the second relay station; and designating the second wireless resource as a primary wireless resource for the second relay station.

System and method for reusing wireless resources in a wireless network

An optical node for optical burst transport includes optical components operable to transmit and receive optical signals over an optical transmission medium. The optical components include a demultiplexer that is operable to receive a wavelength division multiplexed (WDM) optical signal at an input port and to separate the WDM optical signal into two or more constituent wavelength signals, and a switching matrix that includes one or more electro-optic switches. Each electro-optic switch is operable to receive a wavelength signal and switch the signal to one of two outputs, and the outputs include an output port of the optical node and one or more drop output ports of the optical node.

Optical burst transport using an electro-optic switch

A network provides fault tolerant network routing by identifying root nodes that provide cover against a particular type of fault. Nodes then route copies of packets through these root nodes such that an occurrence of the particular type of fault will not disrupt delivery of the packets.

Fault tolerant network routing

Techniques are described for intelligently allocating bandwidth in a wireless mesh network. The wireless mesh network includes a nodes and links interconnecting the nodes. In order to increase capacity and avoid congestion in the network, a network administrator may regulate network traffic by adjusting various parameters that control the operation of network nodes. The network administrator may identify topology information, which indicates a configuration of the nodes and links, and a traffic matrix, which indicates a relative traffic demand weighting for each source node-destination node pair. From this information, the network administrator may calculate a bandwidth assignment for each link. Network administrator may use the bandwidth assignments to calculate a parameter for each node. That parameter may affect the amount of bandwidth used by a node. These parameters may be transmitted to their respective nodes.

Traffic engineering on wireless mesh networks

A method for managing network traffic includes provisioning an internet protocol (IP) network for communicating traffic. The IP network comprises a plurality of nodes coupled by IP links. The method includes monitoring the IP network for a congestion event and, upon detecting a congestion event, selecting a label switched path (LSP) of the IP network for reroute. The method includes computing a hybrid path route for the selected LSP between a first node and a second node of the plurality of nodes. The hybrid path route comprises at least one lightpath of a wavelength division multiplex (WDM) topology coupled to the IP network. The method also includes determining whether performance of the hybrid path route for the selected LSP reduces costs and, if the hybrid path route reduces costs, activating a new IP link on each of the at least one lightpaths of the WDM topology and rerouting the selected LSP according to the hybrid path route.

Method and system for managing network traffic

A method for token-controlled data transmission includes receiving a token including transmission data specifying one of a plurality of data channels and a time window. A burst blocker is configured, based at least in part on the transmission data, for the selective communication of the specified data channel on an optical transmission medium having the plurality of data channels. The selective configuration of the burst blocker includes splitting the specified data channel from the plurality of data channels, configuring the burst blocker in a first configuration during a time other than the time window to rejoin the specified data channel with the plurality of data channels for transmission of the plurality of data channels toward a destination node, and configuring the burst blocker in a second configuration during the time window to block the specified data channel to prevent the transmission of the specified data channel.

Dynamic blocking of token-controlled data transmissions in communication networks

A network includes multiple nodes interconnected to form a ring topology. These nodes support data transmissions over the network using tokens. To send and receive data over the network, nodes may process control messages. A node can receive a token authorizing transmission on one of multiple data channels, generate a transmission control message identifying a destination node and the authorized data channel, and communicate the transmission control message for receipt by the destination node. The node can also transmit data on the authorized data channel after communicating the transmission control message and communicate the token to a next node.

Token-controlled data transmissions in communication networks

A network includes multiple nodes interconnected to form a mesh topology. These nodes support working paths for the transmission of data and protection paths to provide for recovery in the event of failures on working paths. To select protection paths, elements of the network consider timing constraints associated with failure recovery.

Time constrained failure recovery in communication networks

A network includes multiple nodes interconnected to form a ring topology. These nodes support data transmissions over the network using tokens. To send and receive data over the network, nodes may process control messages. A node can receive a first token authorizing transmission on one of multiple data channels, generate a transmission control message identifying a destination node and the authorized data channel, and communicate the transmission control message to a next node. The node can also communicate a second token to the next node authorizing secondary transmissions on the authorized data channel, transmit data on the authorized data channel after communicating the transmission control message, and communicate the first token to the next node after communicating the second token to the next node.

Data transmissions in communication networks using multiple tokens

Network traffic may be estimated using samples of network activities to identify traffic parameters. A model of the network may be generated using the traffic parameters, and the model can be used to simulate the network using a modified set of parameters. Network traffic may be managed using the results of the simulation. Network traffic can also be managed by intercepting and modifying a control message on a peer-to-peer network.

Estimating and managing network traffic

A method and apparatus for selecting failure protection paths in a WDM network. The method exploits wavelength reservation sharing potentials presented by non-concurrent failure events on a plurality of links sharing a link in a protection path. Light-weight aggregated link metrics termed 'buckets' are used to track wavelength reservations for protection paths on individual links in the network. These buckets are then used to construct protection paths with minimized wavelength consumption. The method is employed on individual networking devices in a distributed manner or is used by a centralized network management system to allocate protection paths.

Online distributed path routing method and system

A method and system of combining a plurality of parallel communication channels to emulate a single high-bandwidth communication channel. A continuous stream of packets are grouped as traffic aggregates and assigned to queues associated with the plurality of parallel communication channels. The assignment and reassignment of traffic aggregates to the queues is performed dynamically based on measuring the queue load ratios associated with the lengths of the queues for each of the parallel communication channels. Grouping of existing and future packets as traffic aggregates is based on common attributes shared by the packets such as common source and destination IP addresses.

Growing community of inventors

Milpitas, CA, United States of America

Ching-Fong Su