A Fault Detection Algorithm for Cloud Computing Using QPSO-Based Weighted One-Class Support Vector Machine

The complexity and diversity of cloud computing bring about cloud faults, which affect the quality of services. Existing fault detection methods suffer problems such as low efficiency and low accuracy. In order to improve the reliability of the cloud data center, a fault detection algorithm based on weighted one-class support vector machine (WOCSVM) is proposed to detect and identify the host faults in the cloud data center. Specifically, first, we conduct correlation analysis among monitoring metrics and select key ones for reducing the complexity. Second, for imbalanced monitoring dataset, one-class support vector machine is used to detect and identify host faults, and a weight allocation strategy is proposed to assign weights to the samples, which describes the importance of different sample points in order to improve detection accuracy on potential faults. Finally, for the purpose of increasing the accuracy further, the parameters are set via a parameter optimization algorithm based on quantum-behaved particle swarm optimization (QPSO). Furthermore, experiments by comprising with similar algorithms, demonstrate the superiority of our algorithm under different classification indicators.