End-to-End Requirements Mapping for Cloud-Native Applications Using ML Models
Bibliographic record
Abstract
In the rapidly evolving landscape of 5G and emerging 6G networks, ensuring cloud-based applications meet stringent performance and reliability requirements is critical to maintaining a competitive edge and satisfying user demands. These applications are typically composed of interconnected components, such as Virtual Network Functions (VNFs) or microservices, each contributing to the application's overall performance. However, configuring individual VNFs or microservices to meet specific end-to-end requirements—such as latency and throughput—poses a significant challenge. Current methods often rely on manual configurations, which can lead to inefficiencies and suboptimal resource use in dynamic cloud environments. In this paper, we introduce a machine learning-based solution to automate the mapping of end-to-end requirements into individual KPI requirements for each component (e.g., VNF) in the service graph. Using Deep Neural Networks (DNN) and Graph Neural Networks (GNN), our solution learns from diverse deployment scenarios and end-to-end application requirements, enabling accurate prediction of the KPIs needed for each component to support overall performance goals. This approach ensures that all components are precisely configured to meet end-to-end requirements without extensive manual tuning. Our evaluation on two distinct applications demonstrates high accuracy in predictions, achieving up to 98.99% accuracy during training and up to 96.67% in inferencing, surpassing the accuracy of expert-configured setups.
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 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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 teacher head, 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".