A mobility and bandwidth prediction controller using an adaptive neuro-fuzzy inference system for mobile ad hoc and sensor networks

Abstract

In this paper, we propose a new fuzzy neural controller for a mobility and bandwidth prediction in mobile ad hoc and sensor networks. The bandwidth prediction is based on an Adaptive Neuro-Fuzzy Inference System (ANFIS) that we realized. The built controller is adaptive in the sense that it can learn and predict future location and bandwidth requirements for mobile nodes. As a result, a significant reduction of computational time was obtained. The performance of our controller was evaluated using the mobility data. The performance measure of our controller shows that the prediction of movement and the required bandwidth have a high accuracy ratio regardless of the speed of mobile nodes. © 2009 Springer Berlin Heidelberg.