An ensembled multi-layer automatic-constructed weighted online broad learning system for fault detection in cellular networks

6G is desired to support more intelligence networks and this trend attaches importance to the self-healing capability if degradation emerges in the cellular networks. As a primary component of self-healing networks, fault detection is investigated in this paper. Considering the fast response and low time- and-computational consumption, it is the first time that the Online Broad Learning System (OBLS) is applied to identify outages in cellular networks. In addition, the Automatic-constructed Online Broad Learning System (AOBLS) is put forward to rationalize its structure and consequently avoid over-fitting and under-fitting. Furthermore, a multi-layer classification structure is proposed to further improve the classification performance. To face the challenges caused by imbalanced data in fault detection problems, a novel weighting strategy is derived to achieve the Multilayer Automatic-constructed Weighted Online Broad Learning System (MAWOBLS) and ensemble learning with retrained Support Vector Machine (SVM), denoted as EMAWOBLS, for superior treatment with this imbalance issue. Simulation results show that the proposed algorithm has excellent performance in detecting faults with satisfactory time usage.