No abstract

No abstract

In this paper we investigate the interaction between TCP and wireless ARQ mechanisms. The aim is to understand what is the best reliability degree of the wireless link in order to guarantee TCP performance. For this purpose, we first develop a Markov model for a selective repeat ARQ protocol, widely used in the current wireless environments. Secondly, we design a crosslayer algorithm that, by exploiting the proposed model, can adapt the number of link layer transmission attempts to the end-to-end packet loss rate perceived by TCP. The interaction between TCP and link layer is evaluated in a specific case study (TCP over 3G radio access) by means of simulations carried out by using a very detailed UMTS-TDD simulator based on ns. The deployment of the link layer Markov model and of the proposed algorithm allows us to derive some interesting conclusions about the design of retransmission protocols in TCP/IP network environments.

In this paper we describe and validate the analytic model of a mixed TCP Reno and TCP Vegas network scenario. There is experimental evidence that TCP Vegas overcomes the widespread TCP version, called TCP Reno, in a number of network environments. The incompatibility between TCP Vegas and TCP Reno in heterogeneous network scenarios has been also verified by means of several simulations. The model presented in this work allows to quantitatively evaluate this incompatibility, by computing the average throughput of a TCP Vegas source in presence of a concurrent TCP Reno source. This model can help us to better understand the reasons of the vulnerability of TCP Vegas in competing with TCP Reno sources.

No abstract