Ksurf+: Attention Kalman Filter for Prediction Under Highly Variable Cloud Workloads
Bibliographic record
Abstract
Resource estimation and workload forecasting are critical in cloud data centers. Complexity in the cloud provider environment due to varying numbers of virtual machines introduces high variability in workloads and resource usage, making estimations problematic using state-of-the-art models that fail to deal with nonlinear characteristics. High measurement noise and variance affect the estimation of resource metrics of cloud systems across packet networks influenced by unknown external dynamics. An ideal solution to these problems is the Kalman filter, a variance-minimizing estimator, ideal for highly variable data. This work introduces Ksurf+, a novel Kalman filter estimator using selective principal component analysis and an attention mechanism for enhanced short-horizon prediction. Ksurf+ improves prediction accuracy by 37% over state-of-the-art Kalman filters in prediction tasks, reduces the time series prediction error of the state-of-the-art Bi-directional Grid Long Short-Term Memory neural network by over 40%, improves Kafka workload-based scaling stability by 58%, reduces Kafka queue size and lowers Kubernetes worker pod CPU usage by 11.6% on the$VarBench$benchmark.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".