Rate-controlled optical burst switching

Abstract

The invention provides a method and network communication equipment for low latency loss-free burst switching. Burst-transfer schedules are determined by controllers of bufferless core nodes according to specified bitrate allocations and distributed to respective edge nodes. In a composite-star network, burst schedules are initiated by any core node. Burst formation takes place at source edge nodes and a permissible burst size is determined according to an allocated bitrate of a burst stream to which the burst belongs. The permissible burst size is subject to constraints such as permissible burst-formation delay, a minimum guard-time requirement, and permissible delay jitter. A method of control-burst exchange between each edge node and each bufferless core node enables burst scheduling, time coordination, and loss-free burst switching. Both the payload bursts and control bursts are carried by optical channels connecting the edge nodes and the core notes.

What is claimed is: 
     
         1 . A communication network comprising:
 a plurality of edge nodes; and   a plurality of core switching nodes, each core switching node comprising at least one optical switch having no traffic buffers, a selected core switching node of the plurality of core switching nodes being configured to:
 receive, from a source edge node of the plurality of edge nodes, a bit rate allocation request specifying a destination edge node of the plurality of edge nodes; 
 generate, in response to the bit allocation request, at least one burst transfer permit, each burst transfer permit specifying a respective permissible burst size, an inter-burst interval and the destination edge node; and 
 send the at least one burst transfer permit to the source edge node. 
   
     
     
         2 . The network of  claim 1 , wherein the source edge node is configured to:
 receive from the selected core switching node, the at least one burst transfer permit;   assemble at least one data burst having a burst size not exceeding the respective permissible burst size specified in the burst transfer permit; and   send the at least one data burst to the selected core switching node.   
     
     
         3 . The network of  claim 2 , wherein the respective permissible burst size has an upper bound constrained by a maximum jitter tolerance of data constituting the assembled data bursts. 
     
     
         4 . The network of  claim 2 , wherein:
 each burst transfer permit specifies an arrival time for a data burst at the selected core switching node; and   the source edge node is configured to send the at least one data burst from the source edge node to the selected core switching node by timing the sending of a data burst based on the arrival time specified in a corresponding burst transfer permit.   
     
     
         5 . The network of  claim 1 , wherein the selected core switching node is configured to:
 receive, from the edge node, at least one data burst based at least in part on the at least one burst transfer permit; and   optically switch the at least one data burst to the destination edge node.   
     
     
         6 . The network of  claim 1 , wherein:
 the data of data bursts switched by the selected core switching node comprises data of at least one service; and   the respective permissible burst size has an upper bound constrained by a delay tolerance of the at least one service switched by the selected core switching node.   
     
     
         7 . The network of  claim 1 , wherein the respective permissible burst size has a lower bound much larger than a time required for reconfiguring the at least one optical switch and a maximum arrival time error for data bursts arriving at the at least one optical switch. 
     
     
         8 . The network of  claim 1 , wherein each burst transfer permit specifies an arrival time for a data burst at the selected core switching node. 
     
     
         9 . The network of  claim 1 , wherein the plurality of core switching nodes are configured to:
 receive, from respective source edge nodes of the plurality of edge nodes, a plurality of respective bit rate allocation requests, each respective bit rate allocation request specifying a respective destination edge node;   generate, in response to the respective bit allocation requests, respective burst transfer permits, each respective burst transfer permit specifying a respective permissible burst size, a respective inter-burst interval and a respective destination edge node, each respective permissible burst size having an upper bound constrained by a delay tolerance of services switched by the core switching nodes; and   send the respective burst transfer permits to the respective source edge nodes.   
     
     
         10 . The network of  claim 9 , wherein the edge nodes of the plurality of edge nodes are configured to:
 receive, from respective core switching nodes, respective burst transfer permits; and   assemble, in response to the respective burst transfer permits, respective data bursts having a burst sizes not exceeding the respective permissible burst sizes specified in the respective burst transfer permits; and   send the respective data bursts from the respective source edge nodes to the respective core switching nodes.   
     
     
         11 . The network of  claim 10 , wherein:
 each respective burst transfer permit specifies a respective arrival time for a respective data burst at the respective core switching node; and   the respective edge nodes are configured to send the respective data bursts to the respective core switching nodes by timing the sending of the respective data bursts based on respective arrival times specified in respective corresponding burst transfer permits.   
     
     
         12 . The network of  claim 9 , wherein the respective core switching nodes are configured to:
 receive, from the respective edge nodes, respective data bursts based at least in part on the respective burst transfer permits; and   switch the respective data bursts to respective destination edge nodes.   
     
     
         13 . The network of  claim 9 , wherein the respective permissible burst sizes have a lower bound much larger than a time required for reconfiguring the optical switches and a maximum arrival time error for data bursts arriving at the optical switches. 
     
     
         14 . The network of  claim 9 , wherein each respective edge node is configured to simultaneously transfer respective data bursts to plural core switching nodes of the plurality of core switching nodes. 
     
     
         15 . The network of  claim 14 , wherein at least some edge nodes of the plurality of edge nodes are co-located with respective core switching nodes of the plurality of core switching nodes, and the plurality of edge nodes and the plurality of core switching nodes are configured to equalize propagation delays from respective edge nodes to respective core switching nodes. 
     
     
         16 . The network of  claim 14 , wherein the plurality of edge nodes and the plurality of core switching nodes are configured to time lock respective edge nodes to respective core switching nodes. 
     
     
         17 . The network of  claim 9 , wherein the plurality of edge nodes and the plurality of core switching nodes are configured to:
 associate respective data bursts with respective burst streams; and   size the respective data bursts based at least in part on at least one attribute of the respective burst streams.   
     
     
         18 . The network of  claim 17 , wherein the at least one attribute of the respective burst streams comprises a service class. 
     
     
         19 . The network of  claim 9 , wherein the plurality of edge nodes and the plurality of core switching nodes are configured:
 to associate respective data bursts with respective burst streams; and   to switch all respective data bursts of each respective burst stream in a respective core switching node.   
     
     
         20 . The network of  claim 1 , wherein the bit rate allocation request specifies a requisite bit rate. 
     
     
         21 . The network of  claim 20 , wherein the selected core switching node is configured to determine an update bit rate to replace the requisite bit rate. 
     
     
         22 . The network of  claim 1 , wherein the plurality of core switching nodes is arranged in a composite star configuration.