Hierarchical Forecasts of Cloud Storage Demand with Cost-Sensitive Loss: A Cross-Site Validation Agenda

Abstract

Forecast errors at individual storage pools can accumulate into expensive cloud-capacity decisions. To address this, the study will compare hierarchical demand forecasting strategies under asymmetric penalties for shortages and excess capacity. The research design centres on a rolling-origin evaluation of anonymised utilisation traces across storage pools and service classes. The choice of evaluation units and exclusion criteria is informed by the broader methodological record [3–7]. The analysis will contrast seasonal baselines, independently fitted forecasts and partially pooled hierarchical models. The cross-site extension holds out an entire institution or deployment location rather than relying only on random test splits. Related enterprise-storage studies inform the assessment of operational reliability [1] and the deployment assumptions adopted for system-level comparison [2]. Assessment will focus on capacity breach rates, forecast bias, tail-error cost and the amount of unused provisioned capacity. The supporting evidence base motivates the chosen comparator conditions and robustness criteria [8–12]. Critical sensitivity checks address workload migrations, discontinuous growth, changes in retention policy and service-level constraints. Further systems and modelling literature supplies context for the proposed sensitivity analyses [13–17]. Between-site heterogeneity would be examined through prespecified subgroup estimates and transparent domain-shift diagnostics. The expected output is a reusable evaluation framework with transparent uncertainty and reporting rules, informed by wider reproducibility literature [18–23].