Green Video Transcoding in Cloud Environments Using Kubernetes: A Framework With Dynamic Renewable Energy Allocation and Priority Scheduling
Bibliographic record
Abstract
Video content continues to be a major source of Internet traffic, with a growing demand for high-quality, on-demand videos. This leads to significant energy consumption across cloud servers. Conserving energy and improving energy efficiency in cloud servers is a major challenge. The growing demand for video transcoding services and increasing concerns over energy consumption necessitate systems that balance processing power with energy usage. The research addresses these challenges by developing a green, energy-aware video transcoding system that predicts energy availability from renewable sources (solar and wind) using machine learning techniques and optimizes tasks allocation. The system utilizes a Kubernetes-managed backend to dynamically scale resources for FFmpeg-based transcoding while prioritizing renewable energy, minimizing grid usage utilizing the advanced machine learning models, including Random Forest, XGBoost, and CatBoost, predict energy production and guide task assignments. The integration of predictive analytics with Kubernetes’ Horizontal Pod Autoscaler (HPA) allows dynamic workload distribution, ensuring optimal energy utilization. Additionally, the system incorporates real-time energy monitoring to adjust task scheduling based on fluctuations in renewable energy availability. Two novel scheduling algorithms, Dynamic Renewable Energy Allocation (DREA) and Energy-Aware Priority Scheduling (EAPS), enhance energy efficiency. DREA allocates tasks to energy zones based on real-time renewable availability, while EAPS prioritizes tasks by urgency and energy needs, deferring low-priority tasks to periods of high renewable availability. These green strategies minimize reliance on non-renewable sources while maintaining performance and scalability. The system’s modular design allows easy integration with various cloud platforms, increasing its applicability in real-world scenarios. Furthermore, extensive scalability tests demonstrate that the proposed approach maintains efficient task execution even under high workloads, making it suitable for large-scale cloud environments. By reducing energy consumption and carbon footprint, this framework contributes to the advancement of sustainable cloud computing solutions.
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 | 0.001 |
| 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".