Junho Park  Joyce Jiyoung Whang

10.5626/JOK.2025.52.4.341

microservice system Root Cause Analysis anomaly propagation resource-sharing dependency causality graph resource graph

Identifying root causes of failures in microservice systems remains a critical challenge due to intricate interactions among resources and propagation of errors. We propose AnoProp, a novel model for root cause analysis to address challenges by capturing inter-resource interactions and the resulting propagation of anomalies. AnoProp incorporates two core techniques: the anomaly score measurement for metrics using regression models and the root cause score evaluation for resources based on the propagation rate of these anomalies. Experimental results using an Online Boutique dataset demonstrated that AnoProp surpassed existing models across various evaluation metrics, validating its ability to provide balanced performance for different types of root causes. This study underscores the potential of AnoProp to enhance system stability and boost operational efficiency in microservice environments.