A Cooperative Outage Detection Approach Using an Improved RBF Neural Network with Genetic ABC Algorithm

Abstract

Outage detection in wireless networks is a significant problem of self-healing in SON. In this paper, we propose a cooperative outage detection paradigm using the RBF neural network improved by a genetic artificial bee colony(IRBFG) algorithm for global optimum of neural network parameters and better classification of nonlinear user data. Spatial and temporal features are selected through an improved decision tree base learner for better performance. The simulation results demonstrate that the proposed scheme receives higher detection accuracy and reduces data transmission, especially in the dense small cell network environment.