SAIMD: A Novel False Congestion Detection Scheme in TCP over OBS Networks

Due to the bufferless nature, TCP over Optical Burst Switched (OBS) networks suffer from false congestion detection, where a packet loss event due to random burst contention in a lightly-loaded OBS network may trigger TCP congestion control mechanisms, thereby degrading the performance of TCP. This phenomenon is particularly serious for the TCP flows with very high bandwidth, where returning to slow start due to false congestion detection would critically impair the TCP services and network performance. This paper introduces a novel congestion control scheme for high-bandwidth TCP flows over OBS networks, called Statistical Additive Increase Multiplicative Decrease (SAIMD). SAIMD maintains and analyzes a number of previous round trip time (RTTs) at the TCP senders in order to identify the confidence with which a packet loss event is due to network congestion. The confidence is derived by positioning short-term RTT in the spectrum of longterm historical RTTs. The derived confidence corresponding to the packet loss is then taken in the developed policy for TCP congestion window adjustment. We will show through extensive simulation that the proposed scheme can effectively solve the false congestion detection problem and significantly outperform the conventional TCP counterparts without losing fairness. The advantage gained in our scheme is at the expense of introducing more overhead in the SAIMD TCP senders. Based on the proposed congestion control algorithm, a throughput model is formulated, and is further verified by simulation results.