Packet recovery and error correction in high-speed wide-area networks

The author presents a novel technique for reducing packet loss rate in high-speed wide-area networks in which the BER (bit-error rate) is low. Grouping packets into blocks and adding a packet that computes parity over bits of all packets in a block allow a data recipient to reconstruct any single packet in a block, using the other packets and the block parity packet. The missing packet is identified by observing a sequence-number gap in the stream of incoming packets. Adding another packet containing parity information over the diagonals of a series of blocks allows the decoder to correct a single bit error and reconstruct a missing packet, both occurring in the same block. The performance of the scheme was evaluated using a model of a single-server, discrete-time, finite-capacity queue. It was found that, if the input rate of packets to the queue is such that the packet rejection probability is 10^-3 and below, it is possible to find a proper value of block size for which the decoding yields a substantial reduction in packet loss rate. Further reductions are possible if the server discards not necessarily newly arrived packets but takes into consideration their block affiliations and attempts to distribute the rejected packets among the blocks to maximize the decoding capability