Abstract: A simple access device provides access to a high-capacity network to a traffic source. Once connected to a traffic source, an edge module in the high-capacity network can assign a sub-network address to the traffic source so that the source may also serve as a sink for data traffic. Although the sub-network address assigned to the traffic source may bear little resemblance to a network address for the edge module, distant edge modules may route traffic to a traffic sink having such a sub-network address easily and flexibly. Features may be added to the access device, which would otherwise be little more than a multiplexer, but, for the most part, the edge modules make the routing decisions. Data transfer from the current Internet to the high-capacity network and vice versa can be facilitated by requiring that each edge module in the high-capacity network that acts as a gateway be bilingual, that is, understand both a simple high-capacity network-specific routing protocol and conventional Internet protocols.

Abstract: A method is described for segmenting a data stream comprising variable-size packets, a data stream being defined by its source node, sink node, assigned network route, and other attributes. The segments are of equal size and the method concatenates the packets in successive segments in a manner that attempts to minimize segmentation waste without undue delay. The method facilitates the construction of efficient networks that scale to very high capacities while respecting service-quality specifications. Apparatus for implementing the method are also described.

Abstract: A scaleable high-capacity network comprises several non-uniform composite-star networks interconnected by a number of lateral uniform composite-star networks, thus forming an irregular two-dimensional network. Each non-uniform composite star network comprises electronic edge nodes, possibly of significantly different capacities, interconnected by optical core nodes. The optical core nodes are not connected to each other, and each may be configured differently and have a different reach index, where the reach index of a core node is the number of edge nodes to which the core node directly connects. The selection of a route through a core node within a non-uniform composite-star network is based on a composite index determined according to the reach index of the core node and the propagation delay along the route.

Abstract: In a communication network comprising nodes and links between the nodes, a controller node disseminates routing information including nodal routing tables. A nodal routing table for a given node comprises alternate routes from the given node to other nodes in the network. A controller of the network receives traffic information from nodes and, based on the received traffic information, determines a set of adaptive routing information corresponding to each said node and transmits each set of adaptive routing information to the respective node. Determining the set of adaptive routing information is performed according to a courteous routing scheme. The routing scheme is labeled as “courteous” because, in a contention state, a node-pair that would suffer the least by directing a part of its traffic away from a preferred path yields to node pairs that suffer more by redirecting their traffic. Courteous routing increases the payload throughput and decreases real-time processing effort.

Abstract: A polyphase circulating switch includes switch modules interconnected through a multiplicity of rotators preferably arranged in complementary groups of opposite rotation directions. A polyphase circulating switch having a low switching delay is derived from a multi-rotator circulating switch by providing programmable rotators having adjustable relative rotator-cycle phases. A low delay high-capacity switch may also be constructed from prior-art medium-capacity rotator space switches with mutually phase-shifted rotation cycles. A network comprising several constellations of switch modules distributed over a wide geographic area, where the switch modules of each constellation are interconnected through a rotator assembly, is also disclosed. A rotator assembly may comprise an array of rotators and a master controller for data-transfer scheduling and time-coordination.

Abstract: A circulating switch comprises switch modules of moderate capacities interconnected by a passive rotator. Data is sent from a one switch module to another switch module either directly, traversing the rotator once, or indirectly through at least one intermediate switch module where the rotator is traversed twice. A higher capacity extended circulating switch is constructed from higher-capacity switch modules, implemented as common memory switches and having multiple ports, interconnected through a multiplicity of rotators preferably arranged in complementary groups of rotators of opposite rotation directions. A polyphase circulating switch having a low switching delay is derived from a multi-rotator circulating switch by providing programmable rotators having adjustable relative rotator-cycle phases. A low delay high-capacity switch may also be constructed from prior-art medium-capacity rotator space switches with mutually phase-shifted rotation cycles.

Abstract: In a communication network comprising nodes and links between the nodes, a controller node disseminates link state information. A nodal routing table exists at each node comprising routes between pairs of nodes. The nodal routing table is either populated by the given node based on network information received from the controlling node or populated at the controlling node and received by the given node. Each node receives heartbeat signals from its neighbouring nodes. An unexpected delay between heartbeat signals may be perceived as a failure of a link. The perceived failure of that link is reported by the perceiving node to the controlling node. Upon receiving link failure information from a node, the controlling node may determine a subset of nodes in the network influenced by the link failure and indicate the link failure to the determined subset of influenced nodes.

Abstract: A simple access device provides access to a high-capacity network to a traffic source. Once connected to a traffic source, an edge module in the high-capacity network can assign a sub-network address to the traffic source so that the source may also serve as a sink for data traffic. Although the sub-network address assigned to the traffic source may bear little resemblance to a network address for the edge module, distant edge modules may route traffic to a traffic sink having such a sub-network address easily and flexibly. Features may be added to the access device, which would otherwise be little more than a multiplexer, but, for the most part, the edge modules make the routing decisions. Data transfer from the current Internet to the high-capacity network and vice versa can be facilitated by requiring that each edge module in the high-capacity network that acts as a gateway be bilingual, that is, understand both a simple high-capacity network-specific routing protocol and conventional Internet protocols.

Abstract: In a communication network comprising nodes and links between the nodes, a controller node disseminates routing information including nodal routing tables. A nodal routing table for a given node comprises alternate routes from the given node to other nodes in the network. A controller of the network receives traffic information from nodes and, based on the received traffic information, determines a set of adaptive routing information corresponding to each said node and transmits each set of adaptive routing information to the respective node. Determining the set of adaptive routing information is performed according to a courteous routing scheme. The routing scheme is labeled as “courteous” because, in a contention state, a node-pair that would suffer the least by directing a part of its traffic away from a preferred path yields to node pairs that suffer more by redirecting their traffic. Courteous routing increases the payload throughput and decreases real-time processing effort.

Abstract: A high-capacity switch for transferring variable-sized packets under rate control is described. The packets are divided in the switch into segments of predetermined equal size. The packets are reconstructed before egress from the switch. The switch serves traffic of different classes of service, but the class of service distinction is relevant only at the ingress or egress modules. The switch control is preferably centralized to facilitate effective sharing of the inner capacity of the switch. The control is based on modulating the ingress/egress rate according to traffic load, the central control being unaware of the class of service disposition of the traffic it controls. The advantage is a high capacity switch adapted to transfer variable-sized packets with guaranteed rate control.

Abstract: A wide-coverage high-capacity network that scales to multiples of petabits per second is disclosed. The network comprises numerous universal edge nodes interconnected by numerous disjoint optical core connectors of moderate sizes so that a route set for any edge-node-pair includes routes each of which has a bounded number of hops. A core connector can be a passive connector, such as an AWG (arrayed wave-guide grating) device, or an active connector such as an optical channel switch or an optical time-shared channel switch. The core capacity is shared. Thus, failure of a proportion of core connectors reduces network connectivity but does not result in a major service discontinuity.

Abstract: In a communication network comprising nodes and links between the nodes, a controller node disseminates link state information. A nodal routing table exists at each node comprising routes between pairs of nodes. The nodal routing table is either populated by the given node based on network information received from the controlling node or populated at the controlling node and received by given node. Each node receives heartbeat signals from its neighbouring nodes. An unexpected delay between hearbeat signals may be perceived as a failure of a link. The preceived failure of that link is reported by the perceiving node to the controlling node. Upon receiving link failure information from a node, the controlling node may determine a subset of nodes in the network influenced by the link failure and indicate the link failure to the determined subset of influenced nodes.

Abstract: An optical shell node is provided with an ability to perform time switching on signals received from subtending edge nodes and channel switching on signals received from other shell nodes and destined for the subtending edge nodes. The signals received from the subtending edge nodes may be aggregated into signals that are channel switched by optical core nodes or by other shell nodes toward destination edge nodes. A resultant network formed of these shell nodes along with channel-switching core nodes and subtending-upon-shell-node edge nodes is capable of expansion beyond a continental scale, can support large numbers of edge nodes and has a higher bit rate capacity than known optical network structures.

Abstract: A high-capacity switch for transferring variable-sized packets under rate control is described. The packets are divided in the switch into segments of predetermined equal size. The packets are reconstructed before egress from the switch. The switch serves traffic of different classes of service, but the class of service distinction is relevant only at the ingress or egress modules. The switch control is preferably centralized to facilitate effective sharing of the inner capacity of the switch. The control is based on modulating the ingress/egress rate according to traffic load, the central control being unaware of the class of service disposition of the traffic it controls. The advantage is a high capacity switch adapted to transfer variable-sized packets with guaranteed rate control.

Abstract: A high-speed wavelength-division multiplexed (WDM) network that provides compliant, “invisible” paths of adaptive capacity from an external information source to an external information sink is described. The WDM network includes a plurality of high-speed electronic edge switch modules that are connected by WDM optical links to parallel-plane switch core modules. Smearing distributors ensure that packets to be transferred to a given output link are distributed evenly among the planes of the core modules. Consequently, contention is resolved. Each edge switch is connected to each core module by a WDM optical link. For purposes of admission control, the capacity of the link, rather than the capacity of channels in the link, is considered. This provides much improved granularity in connection bandwidth. The smallest connection may be a few kb/s, while the largest connection may be link capacity. Each edge switch is also adapted to accept data from external sources in a plurality of formats.

Abstract: A modular optical switch includes a set of optical switch modules connected in a mesh, a master controller for the whole optical node and a switch-module controller for each of the optical switch modules. The optical switch modules receive optical signals from, and transmit optical signals to, edge nodes based on connection requests received from the edge nodes. The master controller acts to select a path, using a simple or compound time-slot matching process, through the mesh of switch modules for each optical signal related to a connection request. Advantageously, the optical switch modules are fast switching, enabling the use of time-sharing schemes such as TDM, and the modular optical core node is made practical by efficient path selection at the master controller. A hybrid modular switch may include both optical and electronic switch modules, a master controller, and a switch-module controller for each of the switch modules.

Abstract: An optical core node that includes optical switching planes interfaces, at input, with multi-channel input links and, at output, with multi-channel output links. The number of channels per link can differ significantly among the links, necessitating that the input (output) links have different connection patterns to the switching planes. Such an optical core node requires new methods of assigning an incoming wavelength channel to one of the optical switching planes. The assignment of the channels of input and output links to input and output ports is established in a manner that increases input-output connectivity and, hence, throughput. Additionally, the networks that may be formed with such optical core nodes require new routing methods. A preferred method of selecting a path through the core node favors switching planes connecting to a small number of links. In a time-division-multiplexing (TDM) mode, the method of path selection is complemented by temporal packing of TDM frames.

Abstract: A multi-class digital network is described. The network supports a plurality of digital services using dynamically-configured service bands to support various transport modes and qualities of service. A network control element receives traffic and network state information from the nodes. The network control element maintains a network topology and uses the network topology to compute route sets for the nodes. The network control element uses the traffic information to compute network size specifications. The switching nodes use rate controllers to divide the capacity of each link among the connection classes according to rules which ensure consistent service attributes for each band across the network. The rate controllers are adapted to support different transport modes and different packet sizes so that the deconstruction and reconstruction of packets at network edge devices is eliminated.

Abstract: The invention relates to scheduling packets from numerous traffic classes that share a common high speed channel. A method and an apparatus for regulating several thousand traffic classes sharing a very high speed common channel of a capacity of the order of 80 Gb/s are described. The packets are generally of variable size, and each channel is assigned a transfer rate less than or equal to the capacity of shared channel, with the sum of transfer rates of all classes not exceeding the capacity of the shared channel. The rare allocation for each class is determined either by operator specification or, preferably, by automated means based on traffic monitoring. In the latter case, the transfer rate allocated to a class may be dynamically updated.

Abstract: A wide-coverage, high-capacity, switching network is modeled after a classical space-time-space switch. In the switching network, each of the space stages comprises geographically distributed optical space switches and the time stage comprises a plurality of geographically distributed high-capacity electronic switching nodes. User-access concentrators, each supporting numerous users, access the network through ports of the distributed optical space switches. A user-access concentrator is a simple device which need only have a single access channel to access the network, although two or more access channels may be used. Such a user-access concentrator can communicate with a large number of other user-access concentrators by time-multiplexing the access channel.