Minimizing Energy Consumption in Data Centers Using \nEmbedded Sensors and Machine Learning
Bibliographic record
Abstract
Cloud Data Centers (DCs) consume extensive amounts of energy, making a significant \ncontribution to environmental concerns. Moreover, with the emergence of 5G and future \nB5G networks, which are increasingly inclined towards software orientation and reliant \non cloud computing, there is an urgent requirement for optimizing the energy consumption \nof DCs. We address this issue by proposing an energy-aware Virtual Machine (VM) \nplacement solution for energy minimization. \nIn the first part of this study, we propose a highly accurate model for predicting the \ndynamic power consumption of cloud computing devices. Our proposal takes advantage \nof the various sensors that are now embedded in physical machines, or more generally in \ncloud server machines, as well as Performance Monitoring Counters (PMCs) to implement \na highly accurate Machine Learning (ML) power prediction model. The core part of this \nstudy then integrates the novel feature space of real-time sensors’ measurements and the \npredictive power model to propose a scalable placement algorithm, enabling proactive and \nenergy-aware Virtual Machine placements. In addition, it utilizes a new set of temperature-related \nfeatures that enables proactive hotspot avoidance. \nOur ML predictive models, as well as our proposed placement algorithm, were extensively \nevaluated on a cluster of real physical machines and demonstrated a significantly \nhigher performance as compared to the implemented reference models and algorithms, reducing \nenergy consumption by up to 7%, CPU temperature by 2%, and overloading by 28%.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".