Key result
The combined causal attribution methodology achieved high accuracy for separated actions and identified the causal rApp in the top-2 candidates in >90% of events with overlapping actions.
Why the study?
When a KPI changes with concurrent rApps running atop the Non-RT RIC, operators cannot systematically determine which rApp action caused it, as existing O-RAN conflict mitigation offers no post-hoc causal attribution.
A novel observability architecture for O-RAN Non-RT RIC successfully attributes KPI changes to specific rApp actions even under concurrent overlapping conditions.
Answers are grounded in this paper and cite their sources.
Supports reliable KPI attribution under concurrent rApp actions; leaves open validation in deployed O-RAN networks.
Concurrent rApps (third-party applications running atop the Non-RT RIC) introduce a fundamental observability gap: when a Key Performance Indicator (KPI) changes, operators cannot systematically determine which rApp action caused it. Existing O-RAN conflict mitigation operates proactively or reactively within the control loop but offers no post-hoc causal attribution.We propose an observability architecture for the Non-RT RIC that captures timestamped rApp actions across the R1, A1, and O1 interfaces, aligns them with KPI time series, and applies a causal attribution methodology combining changepoint detection, Granger causality, conditional intervention effect, and temporal precedence scoring. Evaluation with three concurrent rApps over a simulated multi-cell 5G setup, across three scenarios of increasing difficulty, shows that the combined method achieves high accuracy when actions are temporally or spatially separated and consistently places the causal rApp within the top-2 candidates under concurrent overlapping actions on shared cells.
No takes yet. Share an insight, caveat, or question.
Roberto Riggio (2026) studied this question. Causal attribution methodology vs. Individual scoring methods was evaluated on Attribution accuracy. The combined causal attribution methodology achieved high accuracy for separated actions and identified the causal rApp in the top-2 candidates in >90% of events with overlapping actions.
Synapse has enriched 10 related papers. Consider them for comparative context: