Bibliographic record
Abstract
Server energy consumption has been a subject of research for more than a decade now. With Internet scaling rapidly all over the world, more servers are being added continuously. With global warming and financial cost associated with running servers, it has now become a more pressing concern to optimize the power consumption of these servers while still not affecting the performance. The optimization that can be carried out at the hardware level has its limits and therefore the onus comes on to the software developers as well to optimize their web interacting services and use protocols that are more efficient. Recently, Internet Engineering Task Force (IETF) formalized the specification for the successor of HTTP/1.1 protocol. Named HTTP/2, it has been projected to overcome all the limitations of HTTP/1.1 protocol for which web services developers have to optimize their applications. Understandably, HTTP/2 has been drawing a lot of interest from users, web administrators to big organizations. With HTTP/2 as the future of the Internet communication and servers acting as the backbone of the Internet, we are interested in knowing if HTTP/2 will provide energy efficiency benefits to servers or it will just improve users web experience. In this paper, we evaluate the energy efficiency of two web servers while they communicate over HTTP/1.1 and HTTP/2 protocol. We also investigate how Transport layer security (TLS) affects the power consumption of the servers. In our tests, we have introduced HTTP/2 features one by one so that readers can see for themselves what benefits the HTTP/2 over HTTP/1.1. Our study suggests that multiplexing and Round Trip time (RTT) are the biggest factors helping HTTP/2 achieve its design goals. We conclude that even with huge TLS associated cost with HTTP/2, on high latency networks it can help servers to be more energy efficient while improving their performance as well.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 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".