Ensemble Learning for Predicting Task Connectivity Over Time in Cloud Data Centers
Bibliographic record
Abstract
The rapid growth and interdependencies of cloud-hosted services and applications have made it imperative to optimize data center resource management while maintaining low operating costs. Inefficient resource use, rising energy consumption, and operating costs impact cloud provider's ability to provide high-quality services on an elastic basis. However, changing the selection and decision-making processes based on how the tasks are set up can improve scheduling and resource management in cloud data centers. In this paper, we develop a multivariate time series prediction model for task connectivity based on windowing characterization and ensemble learning methods. The high cardinality features are handled using a counter encoder, and the task trace data is transformed using a sliding window, from which features are extracted and used in conjunction with the task profile data to train and tune the candidate estimators. The best model outcomes are then used to construct an ensembled estimator. As part of the evaluation, a baseline comparison is performed in order to determine how well ensemble learning predicts task connectivity over time. The model outcomes are assisted using standard classification metrics such as accuracy, precision, and recall, including the F1 score, Kappa, and Matthews correlation coefficient. The results show that the proposed model outperformed the traditional models in most performance metrics, indicating the successful implementation of an ensemble learning approach for task connectivity predictions in large-scale cloud data centers.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".