Bibliographic record
Abstract
Cloud computing is a new computing paradigm and it is gaining wide popularity due to its benefits including reduced cost, ease of management, and increased reliability. In a cloud computing environment, companies or individuals offload their computing (hardware/software/data) to the cloud, which is supported by the computing infrastructure called datacenters. Datacenters consume large amounts of electricity to operate and bring enormous electricity bills to the operators. Associated emissions also cause significant negative impact to the environment. Meanwhile, a new kind of electrical grid, called the smart grid, is emerging. Smart grids enable two way communications between the power generators and the power consumers. Smart grid technology brings many salient features to help deliver power efficiently and reliably. There are many efforts addressing either of the two tracks above. Different with them, we focus on cost-aware datacenter power management in presence of smart grids and review recent developments on this area. It involves understanding how a smart grid operates, where power goes in datacenters, and most importantly, how to reduce the power cost and/or negative environmental impact when operating datacenters. We first study new ideas of exploring spatial diversities provided by geographically distributed datacenters and show how to perform request routing. Then, we discuss the research that leverages temporal flexibilities given by delay-tolerant workload and present how to conduct workload scheduling. Thirdly, we study how to jointly optimize routing and scheduling by considering spatial diversities and temporal flexibilities together. These studies consider multiple features of smart grids, and develop different cost minimization approaches using techniques from the optimization, algorithmic, and feedback control fields. Moreover, we review studies incorporating the same solution framework with additional dimensions such as renewable and cooling.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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".