A holistic analysis of problem and incident tickets in a real production cloud service environment is presented in this paper. By extracting different bags of words, we use principal component analysis (PCA) to examine the clustering characteristics of these tickets. Then K-means and latent Dirichlet allocation (LDA) are applied to show the potential clusters within this Cloud environment. The second part of our study uses a pre-trained bidirectional encoder representation from transformers (BERT) model to classify the tickets, with the goal of predicting the optimal dispatching department for a given ticket. Experimental results show that due to the unique characteristics of ticket description, pre-processing with domain knowledge turns out to be critical in both clustering and classification. Our classification model yields 86% accuracy when predicting the target dispatching department.

As the scale of software systems expands, maintaining their stable operation has become an extraordinary challenge. System logs are semi-structured text generated by the recording function in the source code and have important research significance in software service anomaly detection. Existing log anomaly detection methods mainly focus on the statistical characteristics of logs, making it difficult to distinguish the semantic differences between normal and abnormal logs, and performing poorly on real-world industrial log data. In this paper, we propose an unsupervised framework for log anomaly detection based on generative pre-training-2 (GPT-2). We apply our approach to two industrial systems. The experimental results on two datasets show that our approach outperforms state-of-the-art approaches for log anomaly detection.

Microservices have become popular in enterprises because of their excellent scalability and timely update capabilities. However, while fine-grained modularity and service-orientation decrease the complexity of system development, the complexity of system operation and maintenance has been greatly increased, on the contrary. Multiple types of system failures occur frequently, and it is hard to detect and diagnose failures in time. Furthermore, microservices are updated frequently. Existing anomaly detection models depend on offline training and cannot adapt to the frequent updates of microservices. This paper proposes an anomaly detection approach for microservice systems with multi-source data streams. This approach realizes online model construction and online anomaly detection, and is capable of self-updating and self-adapting. Experimental results show that this approach can correctly identify 78.85% of faults of different types.