Anomaly detection is critical to ensure cloud infrastructures’ quality of service. However, due to the complexity of inconspicuous (indistinct) anomalies, high dynamicity, and the lack of anomaly labels in the cloud environment, multivariate time series anomaly detection becomes more difficult. The existing approaches are rarely effective in meeting these challenges. In this paper, we propose a novel convolutional adversarial model, convolutional-adversarial-training-based integrated anomaly detection with explanation framework (CAT-IADEF), for multivariate time series anomaly detection in the cloud. We adopt three convolutional neural networks to learn sequence features and adversarial training to amplify “slight” anomalies while enhancing the robustness of the model. The dynamic threshold is determined in real time by the peaks over threshold (POT) method to improve detection accuracy. In addition, anomaly explanation is also conducted efficiently by analyzing anomaly score vectors. Experiments with seven data subsets from various public datasets show that CAT-IADEF outperforms state-of-the-art methods. The average F1 score on the seven datasets is 0.907, which is 6.5% higher than the state-of-the-art model and up to 22.1% higher than the baseline method. Furthermore, the proposed anomaly explanation framework is also integrated into various models to verify its effectiveness on the experimental datasets.

In order to improve the accuracy of prediction of tunnel blasting vibration velocity peak value, a case study was carried out in Qinhuangdao Mountain Tunnel through the Great Wall in Hebei Province. The meta-heuristic algorithm is used to optimize the initial weights and thresholds of Elman network, which solves the problem that the traditional neural network is easy to fall into local extreme value and low prediction accuracy in tunnel blasting vibration prediction. The cosine amplitude method was used for sensitivity analysis to evaluate the influence of each parameter on PPV. BAS-Elman prediction model is compared with traditional neural networks and commonly used empirical formulas. It is found that the BAS-Elman model is superior to other neural network prediction models and empirical formulas in terms of prediction accuracy and learning efficiency.