Conformal Monitoring of Storage-Failure Predictors during Workload Drift: A Reproducibility-Centred Evaluation

Abstract

Predictive maintenance systems often report confident failure probabilities even after the underlying workload distribution changes. An evaluation that overlooks these constraints may reach conclusions that cannot be reproduced. This study aims to quantify when conformal uncertainty monitoring can warn of deteriorating failure-prediction reliability. The evaluation would follow a chronologically blocked simulation that calibrates uncertainty on historical storage telemetry and tests later hardware cohorts. The choice of evaluation units and exclusion criteria is informed by the broader methodological record [3–7]. The analysis will contrast fixed-score alarms, probability-calibrated models and rolling conformal warning policies. The reproducibility extension records dataset versions, model settings, exclusion rules and provenance before any held-out evaluation. Prior work on storage operations provides technical context for validation [1], while complementary systems evidence motivates service-continuity checks [2]. Assessment will focus on empirical coverage, alert lead time, false-positive workload and stability under distribution shift. The supporting evidence base motivates the chosen comparator conditions and robustness criteria [8–12]. Critical sensitivity checks address serial dependence, rare-event labelling, replacement hardware and uncertainty during outages. Further systems and modelling literature supplies context for the proposed sensitivity analyses [13–17]. An independent replication exercise would repeat the main analysis from the documented artefacts and quantify disagreements. The expected output is a reusable evaluation framework with transparent uncertainty and reporting rules, informed by wider reproducibility literature [18–23].