Machine Learning-based Energy Aware Placement of Container \nover Virtual Machines
Bibliographic record
Abstract
The advent of 5G and the imminent arrival of Beyond 5G (B5G) have significantly increased demands on service providers. This exponential growth poses a challenge for 5G networks, since clients are currently offloading data to edge cloud servers to meet the connectivity and latency requirements. These servers must continually scale to meet increasing demands for CPU, memory, and storage, leading to significant energy consumption. Data centers account for 1.5% of global energy consumption and produce equally high greenhouse gas emissions. This trend will grow unless we find ways to improve efficiency. Our work proposes a solution to these problems with an efficient placement algorithm backed by an accurate energy predictive model. This model helps by pre-emptively detecting the energy each machine will consume when future tasks are deployed. These predictive \ncapabilities help the placement and reduce overall energy consumption. Our model uses Performance Monitoring Counters and various sensors, such as heat and fan speed, commonly found on Data Center machines, to increase its feature space and accuracy. Our work \nincludes creating the model and integrating it with the energy-aware placement algorithm. Additionally, our method increased the performance and overall Quality of Service. Our results show that our machine learning model, particularly using XGBoost, can reduce energy consumption and improve task completion times in realistic scenarios. Our experiments, tested on real servers with realistic loads, achieved good results without using stresses like stress-ng that generate unrealistic loads. Our model achieved an R2 score of 91.2%, helping reduce energy consumption by 6% without changes to the cluster or the \nneed for consolidation.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 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".