We consider the problem of providing per-customer service guarantees in a high-speed packet switch typically situated at the edge between a set of customers and a service provider network. As basic requirements, the switch should be scalable to high speeds per port, a large number of ports, and a large number of customers (macroflows) with independent guarantees. Existing scalable solutions are based on virtual output queuing, which is computationally complex when required to provide service guarantees for a large number of macroflows. We present a novel architecture for packet switching that provides support for such service guarantees. A cost-effective fabric with small external speedup is combined with a feedback mechanism that enables the fabric to be virtually lossless, thus avoiding packet drops indiscriminate of macroflows' behavior. Through analysis and simulation, we show that this architecture provides accurate support for service guarantees, has low computational complexity, and is scalable to very high port speeds.

Multimedia applications like MPEG-2 video produce packets with multiple levels of importance from application quality point of view. We propose a traffic policing mechanism for such applications, called elastic policing, which provides more flexibility to more important packets. We describe a token bucket based implementation of elastic policing using additional "loan buckets", and verify its performance by simulation studies. We observe significant improvement in objective video quality without increasing traffic admitted into the network in the long term

One of the well-known problems in real-time packetized voice applications is the degradation in voice quality due to delayed or misrouted packets. When a voice packet does not arrive at the receiver on time, the receiver needs a packet loss concealment algorithm to generate a signal instead of the missing voice segment. In this paper we describe a high performance packet loss concealment algorithm for pulse code modulation (PCM) coded speech. The algorithm extracts the residual signal of the previously received speech by linear prediction analysis, uses periodic replication to generate an approximation for the excitation signal of missing speech, and generates synthesized speech using this excitation. It also performs overlap-and-adding and scaling operations to smooth out transitions at frame boundaries. The new algorithm is compared to other algorithms by subjective quality tests, and is found to be better than the existing algorithms in some cases.

Discrete cosine transform (DCT) coding is widely used for compression of rectangularly sampled images. We address efficient DCT coding of nonrectangularly sampled images. To this effect, we discuss an efficient method for the computation of the DCT on nonrectangular sampling grids using the Smith-normal decomposition. Simulation results are provided.>