A Congestion Window Control Mechanism Based on Fuzzy Logic to Improve TCP Performance in MANETs

In Mobile Ad Hoc Networks (MANETs), the TCP performance is significantly degraded due to some characteristics of MANETs such as mobility, multi-hop routing, dynamic topology, distributed control and management. In TCP the sender assumes that packet loss is an indicator of network congestion. However, this assumption may not apply to MANETs. In this paper, the authors have proposed a fuzzy inference system based on the factors of expected throughput and actual throughput to dynamically adjust the congestion window size that lead to improvement in the performance of TCP in MANETs. This proposed scheme does not rely on any explicit feedback from the network, it requires only the sender side modifications. The simulation study of the ad hoc network in this work is with regard to equal sharing of network bandwidth among multiple TCP flows. Through extensive simulations, the authors have shown that the number of concurrent flows significantly affects the TCP performance. The proposed scheme achieves the desired goals of improved performance compared to other TCP variants.