A Proactive Context-Aware Self-Healing Scheme for 5G Using Machine Learning

Future mobile communication networks particularly 5G networks require to be efficient, reliable and agile to fulfill the targeted performance requirements. All layers of the network management need to be more intelligent due to the density and complexity anticipated for 5G networks. In this regard, one of the enabling technologies to manage the future mobile communication networks is Self-Organizing Network (SON). Three common types of SON are self-configuration, Self-Healing (SH) and self-optimization. In this paper, a framework is developed to analyze proactive SH by investigating the effect of recovery actions executed in sub-health states. Our proposed framework considers both detection and compensation processes. Learning method is employed to classify the system into several sub-health (faulty) states in detection process.  The system is modeled by Markov Decision Process (MDP) in compensation process in which the equivalent Linear Programing (LP) approach is utilized to find the action or policy that maximizes a given performance metric. Numerical results obtained in several scenarios with different goals demonstrate that the optimized proposed algorithm in compensation process outperforms the algorithm with randomly selected actions.

Keywords:

component , fifth generation cellular network (5G) , self-organizing networks (SON) , self-healing , fault detection and compensation , markov decision problem (MDP) , linear programming , machine learning , K-means clustering