Hierarchical Forecasts of Cloud Storage Demand with Cost-Sensitive Loss

Abstract

Forecast errors at individual storage pools can accumulate into expensive cloud-capacity decisions. The objective is to compare hierarchical demand forecasting strategies under asymmetric penalties for shortages and excess capacity. Relevant methodological and data-quality literature informs the design of the sampling and validation strategy [3–7]. The proposed method is a rolling-origin evaluation of anonymised utilisation traces across storage pools and service classes. Comparators will include seasonal baselines, independently fitted forecasts and partially pooled hierarchical models. Related enterprise-storage studies inform the assessment of operational reliability [1] and the deployment assumptions adopted for system-level comparison [2]. The design prioritises precise operational definitions and a straightforward baseline before introducing more complex alternatives. Statistical and computational sources help define the reproducibility checks and comparison procedures [8–12]. The primary outcomes are capacity breach rates, forecast bias, tail-error cost and the amount of unused provisioned capacity. Potential biases include workload migrations, discontinuous growth, changes in retention policy and service-level constraints. Primary analyses would be reported by the main deployment or participant subgroup so that averaged results do not conceal systematic failures. Additional research informs the prespecified stress tests and limits on interpretation [13–17]. The intended contribution is an auditable research protocol rather than an unsupported claim of effectiveness; related work frames its transferability limits [18–23].