ML-Assistant Service Function Chaining Workload Scheduler for Cloud-Native inFrastructure
Bibliographic record
Abstract
Service Function Chaining (SFC) has the potential to revolutionize cloud computing and containerization paradigm. SFC jobs, predominantly deployed as containers within cloud-native infrastructures, require substantial computing, memory, and storage resources to operate Virtual Network Functions (VNFs) efficiently. However, scheduling SFC workloads in cloud-native infrastructures, such as Kubernetes clusters spanning geographically distributed data centers, presents significant chal-lenges. These challenges arise not only from the diverse scheduling strategies employed by each data center but also from the vast number of jobs processed on a daily basis. Furthermore, SFC tasks have stringent requirements for computing resources and network bandwidth, which complicates the scheduling process. This paper introduces a machine learning-based (ML-based) scheduling approach to address these challenges by employing the Long Short Term Memory (LSTM) model. This paper makes two main contributions. First, we formulate the dynamic SFC mapping problem by modeling SFC jobs in terms of computing and memory resources. Then, we use a decentralized multiagent LSTM framework to predict the hardware resource usages of nodes for each incoming SFC job, in order to select the most suitable node to optimize system resource utilization and minimize the job wait time. Our results demonstrate a 6%-20% improvement in scheduling efficiency and accuracy compared to non-machine learning-based schedulers.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".