Due to lack of optical RAM buffers in fast optical switches (FOS), statistical multiplexing technologies using FOS like Optical Burst Switching (OBS) or Optical Packet Switching (OPS) are expected to have higher data losses than conventional electronic networks. Consequently, applications transferring data by means of TCP can suffer from a lower throughput. In this paper, we show that this low-throughput problem is mainly an artifact caused by the conventional TCP congestion control algorithms, and can be remedied by using a simple yet effective stop-and-wait congestion control algorithm instead, as long as the propagation delay between TCP source and TCP destination is small compared to the transmission time of an optical packet. We show that such a condition holds for a wide range of scenarios, including fat-tree-based data center networks. We also show that the throughput achieved in a FOS network using stop-andwait can be the same as, or higher than that in an equivalent, conventional electronic network.

No abstract

No abstract

We present the performance of fixed-length, variable-capacity (FL-VC) packets in optical packetswitching (OPS) networks. We show how FL-VC achieves an effective balance between implementation feasibility and performance of the applications using the network. Focusing on metropolitan area networks and real-world file distributions, we also show that an adequate selection of packet duration leads to nearly optimal application throughput with respect to conventional variable-length, fixed-bit-rate packets (VL-FBR), and that this optimal packet duration is robust against changes in the workload. Finally, we show that a single fiber delay line per OPS switch managed by a first-fit scheduler can increase throughput to levels similar to those obtained by random access buffers.