A delay-based approach using fuzzy logic to improve TCP error detection in ad hoc networks

In recent years, a great deal of effort has been devoted to make the TCP protocol more resilient to the random packet losses inherent in the wireless channels in ad hoc networks. In this paper, we investigate the use of fuzzy logic theory for assisting the TCP error detection mechanism in such networks. An elementary fuzzy logic engine is presented as an intelligent technique for discriminating packet loss due to congestion from packet loss by wireless induced errors. The architecture of the proposed fuzzy-based error detection mechanism is also introduced and discussed. The full approach, for inferring the internal state of the network, relies on round trip time (RTT) measurements only. Hence, this is an end-to-end scheme which requires only end nodes cooperation. Preliminary simulation evaluations show how viable this approach may be.