Workload Prediction in Cloud Data Centers Using Complex‐Valued Spatio‐Temporal Graph Convolutional Neural Network Optimized With Gazelle Optimization Algorithm
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
ABSTRACT Workload prediction is the necessary factor in the cloud data center for maintaining the elasticity and scalability of resources. However, the accuracy of workload prediction is very low, because of redundancy, noise, and low accuracy for workload prediction in cloud data center. In this manuscript, Workload Prediction in Cloud Data Centers using Complex‐Valued Spatio‐Temporal Graph Convolutional Neural Network Optimized with Gazelle Optimization Algorithm (CVSTGCN‐WLP‐CDC) is proposed. Initially, the input data is collected from two standard datasets such as NASA and Saskatchewan HTTP traces dataset. Then, preprocessing using Multi‐Window Savitzky–Golay Filter (MWSGF) is used to remove noise and redundant the data. The preprocessed data is fed to CVSTGCN for workload prediction in a dynamic cloud environment. In this work, proposed Gazelle Optimization Approach (GOA) used to enhance the CVSTGCN weight and bias parameters. The proposed CVSTGCN‐WLP‐CDC technique is executed and efficacy based on workload prediction structure is evaluated using several performances metrics such as accuracy, recall, precision, energy consumption correlation coefficient, sum of elasticity index (SEI), root mean square error (RMSE), mean squared prediction error (MPE), and percentage prediction error (PER). The proposed CVSTGCN‐WLP‐CDC provides 23.32%, 28.53% and 24.65% higher accuracy; 22.34%, 25.62%, and 22.84% lower energy consumption when comparing to the existing methods using Artificial Intelligence augmented evolutionary approach espoused cloud data centres workload prediction architecture (TCNN‐CDC‐WLP), Performance analysis of machine learning centered workload prediction techniques for cloud (PA‐BPNN‐CWPC), Machine learning methods for effectual energy utilization in cloud data centers (ARNN‐EU‐CDC) methods respectively.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.003 | 0.000 |
| Research integrity | 0.000 | 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 it