Causal Inference for Root Cause Analysis in Autonomous Networks
Dr. Fatemeh Ghassemi, Prof. Mung Chiang
Purdue University
Abstract
We apply causal inference methods to network root cause analysis, moving beyond correlational ML approaches that often mislead. Our causal discovery algorithm constructs a directed acyclic graph of KPI dependencies from observational network data, enabling identification of true root causes rather than symptoms. On a dataset from a tier-1 operator with 10,000 fault incidents, causal analysis correctly identifies root causes in 88% of cases, compared to 62% for correlation-based methods.
AI Summary
- Causal inference applied to network root cause analysis.
- 88% root cause identification accuracy vs 62% for correlation-based methods.
- Constructs causal DAG of KPI dependencies from observational data.
- Validated on 10,000 real fault incidents from a tier-1 operator.
Key Findings
- 1Correlation-based methods misidentify symptoms as causes in 30% of cases.
- 2Causal graphs reveal hidden dependencies between seemingly unrelated KPIs.
- 3The approach works with observational data without requiring controlled experiments.
Industry Implications
Enables truly autonomous fault management in 6G networks.
Reduces MTTR by identifying actual causes rather than correlated symptoms.
Builds a causal knowledge base that improves with each incident.
Read the Original Paper
Access the full paper on arXiv for complete methodology, results, and references.
Open on arXivRelated Papers
AI Agents for Autonomous Network Operations: Architecture and Evaluation
Rakuten Mobile / NICT Japan — 18 citations
AI + Network PapersAI-Native Air Interface Design: End-to-End Learning for 6G Physical Layer
University of Stuttgart — 41 citations
AI + Network PapersDigital Twin Networks: AI-Driven Real-Time Network Simulation for 6G
Oulu University / Ruhr University Bochum — 29 citations