Protecting IPTV against packet loss: Techniques and trade-offs

Packet loss ratios that are harmless to the quality of data and Voice over Internet Protocol (VoIP) services may still seriously jeopardize that of Internet Protocol television (IPTV) services. In digital subscriber line (DSL)-based access networks, the last mile in particular suffers from packet loss, but other parts of the network may do so too. While on the last mile link, the packet loss is due to bit errors, in other parts of the network it is caused by buffers overflowing or the network experiencing (short) outages due to link or node failures. To retrieve lost packets, the application layer (AL) can use either a forward error correction (FEC) or a retransmission scheme. These schemes, when properly tuned, increase the quality of an IPTV service to an adequate level, at the expense of some overhead bit rate, extra latency, and possibly an increase in channel change time. This paper compares the performance of FEC schemes based on Reed-Solomon (RS) codes with that of retransmission schemes, all tuned to conform to the same maximum overhead bit rate allowed on the last mile link and on the feeder link, and their possible impact on the channel change time. We take into account two kinds of loss processes that can occur: isolated packet losses and burst packet losses. In almost all scenarios, retransmission outperforms FEC.