Optimization of Anomaly Detection in a Microservice System Through Continuous Feedback from Development
Monitoring a microservice system may bring a lot of benefits to development teams such as early detection of run-time errors and various performance anomalies. In this study, we explore deep learning (DL) solutions for detection of anomalous system’s behavior based on collected monitoring data that consists of applications’ and systems’ performance metrics. The study is conducted in a collaboration with a Swedish company responsible for ticket and payment management in public transportation. Moreover, we specifically address a shortage of approaches for evaluating DL models without any ground truth data. Hence, we propose a solution design for anomaly detection and reporting alerts inspired by state-of-the-art DL solutions. Furthermore, we propose a plan for its in-context implementation and evaluation empowered by feedback from the development team. Through continuous feedback from development, the labeled data is generated and used for optimization of the DL model. In this way, a microservice system may leverage DL solutions to address rising challenges within its architecture. CCS CONCEPTS • Software and its engineering → Software post-development issues; • Information systems → Data mining; Computing platforms; • Computing methodologies → Machine learning.