Search

Microservice-based systems (MSS) may experience failures in various fault categories due to their complex and dynamic nature. To effectively handle failures, AIOps tools utilize trace-based anomaly detection and root cause analysis. In this paper, we propose a novel framework for few-shot abnormal trace classification for MSS. Our framework comprises two main components: (1) Multi-Head Attention Autoencoder for constructing system-specific trace representations, which enables (2) Transformer Encoder-based Model-Agnostic Meta-Learning to perform effective and efficient few-shot learning for abnormal trace classification. The proposed framework is evaluated on two representative MSS, Trainticket and OnlineBoutique, with open datasets. The results show that our framework can adapt the learned knowledge to classify new, unseen abnormal traces of novel fault categories both within the same system it was initially trained on and even in the different MSS. Within the same MSS, our framework achieves an average accuracy of 93.26\% and 85.2\% across 50 meta-testing tasks for Trainticket and OnlineBoutique, respectively, when provided with 10 instances for each task. In a cross-system context, our framework gets an average accuracy of 92.19\% and 84.77\% for the same meta-testing tasks of the respective system, also with 10 instances provided for each task. Our work demonstrates the applicability of achieving few-shot abnormal trace classification for MSS and shows how it can enable cross-system adaptability. This opens an avenue for building more generalized AIOps tools that require less system-specific data labeling for anomaly detection and root cause analysis., Comment: 12 pages

Directed graphs (DG), interpreted as state transition diagrams, are traditionally used to represent finite-state automata (FSA). In the context of formal languages, both FSA and regular expressions (RE) are equivalent in that they accept and generate, respectively, type-3 (regular) languages. Based on our previous work, this paper analyzes effects of graph manipulations on corresponding RE. In this present, starting stage we assume that the DG under consideration contains no cycles. Graph manipulation is performed by deleting or inserting of nodes or arcs. Combined and/or multiple application of these basic operators enable a great variety of transformations of DG (and corresponding RE) that can be seen as mutants of the original DG (and corresponding RE). DG are popular for modeling complex systems; however they easily become intractable if the system under consideration is complex and/or large. In such situations, we propose to switch to corresponding RE in order to benefit from their compact format for modeling and algebraic operations for analysis. The results of the study are of great potential interest to mutation testing.