DORA: Efficient Routing for MPLS Traffic Engineering
Journal of Network and Systems Management
Network Bandwidth Predictor (NBP): A System for Online Network performance Forecasting
CCGRID '06 Proceedings of the Sixth IEEE International Symposium on Cluster Computing and the Grid
RLTE: Reinforcement Learning for Traffic-Engineering
AIMS '08 Proceedings of the 2nd international conference on Autonomous Infrastructure, Management and Security: Resilient Networks and Services
QoS online routing and MPLS multilevel protection: a survey
IEEE Communications Magazine
IEEE Journal on Selected Areas in Communications
| Hi-index | 0.00 |
This paper presents an efficient enhancement to the online routing algorithms for the computation of Labeled Switching Paths (LSPs) in Multiprotocol Label Switching (MPLS) based networks. To achieve that, an adaptive predictor is used to predict the future link loads. Then the predicted values are incorporated in the link weights formula. Our contribution is to propose a new idea that depends on the knowledge of the future link loads to achieve a routing that can be done much more efficiently. According to the non-linear nature of traffic, we use a Feed Forward Neural Network (FFNN) to build an accurate traffic predictor that is able to capture the actual traffic behaviour. We study two performance parameters: the rejection ratio and the percentage of accepted bandwidth in different load conditions. Our proposed algorithm in general, reduces the rejection ratio of requests and achieves higher throughput when compared to CSPF and WSP algorithms.