In one embodiment, a first optical network device includes a controller, and a first network interface, wherein the first network interface is configured to exchange data with a first layer 3 network device, and the controller is configured to obtain at least one optical circuit attribute including an optical circuit distance and/or an optical circuit latency of a first optical circuit in an optical network, and provide the at least one optical circuit attribute to the first layer 3 network device. Related apparatus and methods are also described.

An interconnect as a switch module (ICAS module) comprising n port groups, each port group comprising n1 interfaces, and an interconnecting network implementing a full mesh topology where each port group comprising a plurality of interfaces each connects an interface of one of the other port groups, respectively. The ICAS module may be optically or electrically implemented. According to the embodiments, the ICAS module may be used to construct a stackable switching device and a multi-unit switching device, to replace a data center fabric switch, and to build a new, high-efficient, and cost-effective data center.

An interconnect module (ICAS module) includes n optical data ports each comprising n optical interfaces, and an interconnecting network implementing a full mesh topology for interconnecting the optical interfaces of each port each to a respective one of the optical interfaces of each of the other ports. In one embodiment, each optical interface exchanges data signals over a communication medium with optical transceiver. The interconnecting module may implement the full mesh topology using optical fibers. The interconnecting module may be used to replace fabric switches as well as a building block for a spine switch.

A data center network includes a plurality of packet-optical switches each at a location in the data center network and each including a switch fabric comprising both a Layer 1 fabric and a packet fabric communicatively coupled to one or more line ports; wherein the plurality of packet-optical switches are communicatively coupled to one another in a topology to form data connectivity in the data center network, and wherein each of the plurality of packet-optical switches is configured to provide the data connectivity through the Layer 1 switch bypassing the packet fabric when the location does not require Layer 2 forwarding in the topology, and provide the data connectivity through the Layer 1 switch and using the packet fabric to provide the data service with multi-point connectivity when the location requires Layer 2 forwarding in the topology.

A transmission method and system for an optical burst transport network are disclosed in the present document. The method includes: acquiring a topology of a mesh OBTN network, and generating one or more logical sub-networks according to the topology of the mesh OBTN network; a predetermined master node in the mesh OBTN network updating bandwidth maps for all logical sub-networks; the predetermined master node is a node, which all control channels pass through, in all the nodes of the mesh OBTN network.

A data center network includes a plurality of packet-optical switches each at a location in the data center network and each including a switch fabric comprising both a Layer 1 fabric and a packet fabric communicatively coupled to one or more line ports; wherein the plurality of packet-optical switches are communicatively coupled to one another in a topology to form data connectivity in the data center network, and wherein each of the plurality of packet-optical switches is configured to provide the data connectivity through the Layer 1 switch bypassing the packet fabric when the location does not require Layer 2 forwarding in the topology, and provide the data connectivity through the Layer 1 switch and using the packet fabric to provide the data service with multi-point connectivity when the location requires Layer 2 forwarding in the topology.

A matrix M indicating a minimum number of all optical paths between pairs of nodes may be generated in one embodiment using an algorithm for transitive closure. In various embodiments, different algorithms and methods may be used to generate matrix M. Once a convergent matrix M has been generated that attains transitive closure, any corresponding reachability matrix RM^a may be obtained from matrix M in a computationally efficient manner. Matrix M may be used to determine groups of potential regenerator placements and obtain end-to-end optical paths by selecting desired sequences of regenerators.

A matrix M is used to determine groups of potential regenerator placements and obtain potential end-to-end optical paths by selecting desired sequences of regenerators. Then, a hierarchical guided search may be employed to efficiently select desired N-tuple disjoint optical paths from the potential optical paths. The hierarchical guided search may employ a search graph and a search tree to guide the search and to eliminate candidate nodes and optical paths early in the search process.

Examples described herein relate to a network configured according to a topology, where the network is to provide communication between the first computing device and the second computing device. In some examples, the network includes a combination of a connected shuffle box or a bipartite shuffle box. Various examples of connected shuffle boxes and bipartite shuffle boxes are described herein.

Multiple switch planes, each having meshed bufferless switch units, connect source nodes to sink nodes to form a communications network. Each directed pair of source and sink nodes has a first-order path traversing a single switch unit in a corresponding switch plane and multiple second-order paths each traversing two switch units in one of the remaining switch planes. To reduce processing effort and minimize requisite switching hardware, connectivity patterns of source nodes and sink nodes to the switch planes are selected so that each pair of source node and sink node connects only once to a common switch unit. Widely-varying flow rates may be allocated from each source node to the sink nodes. To handle frequent changes of flow-rate allocations, in order to follow variations of traffic distribution, a high-throughput scheduling system employing coordinated multiple scheduler units is provided in each switch plane.