AI-Powered Cloud-Native Observability: Real-Time Anomaly Detection and Root Cause Analysis in Microservices Architectures
Keywords:
Anomaly Detection, Root Cause Analysis, Cloud-Native, Observability, Microservices, Artificial Intelligence, Distributed SystemsAbstract
Purpose:
This paper explores how artificial intelligence (AI) enhances cloud-native observability through real-time anomaly detection and root cause analysis (RCA) in microservices-based architectures.
Design/methodology/approach:
We synthesize findings from key pre-2016 research studies that underpin the evolution of intelligent observability, combining AI/ML with distributed cloud systems and microservices. We introduce two illustrative diagrams and two performance comparison tables for clarity.
Findings:
AI significantly improves system resilience by enabling automatic anomaly detection and effective RCA. Techniques such as time-series analysis, clustering, and causal graph modeling are core to this advancement.
Practical implications:
AI-enhanced observability enables proactive system management, reducing downtime, operational costs, and improving service reliability in dynamic cloud-native infrastructures.
Originality/value:
This paper uniquely positions foundational AI research in the context of contemporary cloud-native operations, demonstrating how earlier studies inform today’s real-time observability needs.
