QoS provisioning by EFuNNs-based handoff planning in cellular MPLS networks

In recent years, Multi Protocol Label Switching (MPLS) has been considered as the preeminent technology to incur Quality of Service (QoS) for integrated services. However, in wireless networks the remotes mobility endangers resource management procedure and QoS provisioning. In this paper we propose a new location prediction method based on Evolving Fuzzy Neural Networks (EFuNNs), to manage Label Switched Paths (LSPs) in an MPLS domain. The proposed predictor employs geographical characteristics of underlying area and the movement history of a remote, to produce a set of confidence ratios as the output. That set is considered as a criterion for establishing and managing LSPs so that QoS preserved. The simulation results have shown superior performance in terms of prediction accuracy and utilization improvement for the proposed methods.