LRS²: Improved Link Recovery in Software-Defined Networks with Stacked Generalization Ensemble

Emerging megatrends like the Internet of Things (IoT), and social and mobile communication technologies are imposing new challenges on the future Internet, for which path reliability is crucial. Traditional IP networks are complex to operate and difficult to configure because they are vertically integrated: data and control plane bundled. The emerging Software-Defined Networking (SDN) architecture breaks vertical integration and separates the control logic from the data plane devices, such as switches and routers, providing a programmable infrastructure for application deployment. As a result, SDN is positioned to compute a reliable path for connected users in the event of a link failure scenario. To minimize the impact of a link failure on ongoing data flows, the prediction of a link failure requires careful attention. Machine Learning (ML) algorithms play a vital role in the link failure prediction process; however, they often have a low detection rate. To achieve a higher link failure detection rate in SDN, there is a need to design an enriched detection architecture, especially when employing ensemble ML models. This work presents LRS2, which is a meta-classification approach using base classifiers to compute a highly reliable data flow path. LRS² utilizes a stacked generalization ensemble, where the base classifiers with low complexity and high diversity receive the original data as input, and each classifier predicts its subproblem. The output is a high degree of accuracy of a metaclassifier in predicting a link's failure. Our experimental study demonstrates that the stacking ensemble has higher accuracy in predicting link failures than other ensembles or single classifiers used in the LRS2.