Loading
Life sciences · Preprint
arXiv · September 3, 2026
Posted before peer review. The findings may change or fail to hold.
This preprint proposes a two-stage cascaded forecasting architecture combining TPS prediction and CPU workload estimation using XGBoost, evaluated on traces from ten production applications. Reported metrics show SMAPE below 7% for most applications and an R² of 0.9185 for the best performer, but the work has not undergone peer review and lacks details on validation methodology, generalization to other cloud environments, and statistical significance testing.
Computational forecasting model evaluated on real-world cloud traces. Ten applications running on a private cloud environment; historical CPU and transaction traces from production workloads.. Intervention: Two-stage XGBoost forecasting model with cascaded learning architecture and expanding-window adaptive retraining.. Compared with: Direct CPU workload forecasting (conventional method); detailed comparative results not numerically reported in abstract.. Private cloud environment; specific geographic location or organization not disclosed..
SMAPE below 7% for most applications in the dataset Best-performing application achieved MAE of 0.7372, RMSE of 1.1866, SMAPE of 3.57%, and R² of 0.9185 Horizon-wise drift analysis showed stable recursive forecasting over 60-step prediction horizon
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is an unrefereed arXiv preprint presenting a computational forecasting method for cloud infrastructure; it lacks peer review and addresses engineering optimization rather than clinical or human health outcomes.
As stated by the source record.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Accurate cloud resource forecasting is essential for proactive resource provisioning, maintaining Quality of Service (QoS), and reducing operational costs in dynamic cloud environments. The existing forecasting approaches predominantly estimate future CPU workload directly from historical resource traces, which often overlook the relationship between customer service demand and subsequent resource consumption. This study proposes a two-stage integrated forecasting model that explicitly models this dependency by first forecasting customer service requests, expressed as Transactions Per Second (TPS), and subsequently estimating future CPU workload from the TPS forecast. Both the forecasting component and resource prediction component employed the XGBoost model within a cascaded learning architecture, complemented by adaptive online retraining using an expanding-window strategy to address concept drift in continuously evolving cloud workloads. The proposed work was evaluated using real-world traces collected from a private cloud environment comprising ten applications. Experimental results demonstrate robust forecasting performance by achieving Symmetric Mean Absolute Percentage Error (SMAPE) below $7\%$ for most applications, with the best-performing application achieving an MAE of $0.7372$, RMSE of $1.1866$, SMAPE of $3.57\%$, and an R2 of $0.9185$. Horizon-wise drift analysis confirmed stable recursive forecasting behavior with controlled error accumulation across a 60-step prediction horizon. Compared with the conventional direct CPU forecasting method, the proposed two-stage integrated model gives improved forecasting robustness, computational efficiency, and interpretability, making it well-suited for proactive resource management and intelligent auto-scaling in cloud computing environments.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.