Delay performance of the new Internet service with guaranteed QoS compared to ATM

In addition to the traditional best-effort IP service of the Internet, the Internet Engineering Task Force has defined new services that provide QoS guarantees on throughput and delay. This article analyses the delay performance that can be achieved with the new service and compares it to the performance that can be obtained by using native ATM. Using a voice and a video application as examples, the end-to-end delay is calculated. Three different scenarios are presented: local, regional and long distance, differing in the distance covered and the number of IP routers traversed. It is shown that when using IP, the achievable end-to-end delay can be kept sufficiently low to support interactive applications with strict delay requirements. The paper further concludes that using native ATM results in a lower delay and in most cases in a higher efficiency than can be achieved with IP.