Energy-Efficient Energy Analytics Using a General Purpose Graphics Processing Unit
Bibliographic record
Abstract
Smart meters allow energy providers to monitor their customers' power consumption. This fine-grained data stream generates many data points, which hides broader trends in power consumption and makes it difficult for energy providers to make decisions regarding a specific customer or a subset of customers. Since the raw power data has little direct use, various algorithms have been proposed to lower the dimensionality of data, discover trends, study relationships between different features of collected data, and summarize data. These analytical techniques make the data more palatable to the end user. Analyzing smart meter data is computationally intensive as there is a large number of households connected to one energy provider, and each household generates years of data at hourly intervals. To speed up the analysis, clusters of commodity computers have been used. Ironically, such clusters consume substantial energy - studies have shown that about 10% of the world-wide supply of electrical power is consumed by the computing infrastructure. In this paper, we describe the use of a graphics processing unit (GPU) to analyze smart meter data, and compare its performance with a conventional multi-core CPU. We discuss the technical challenges in programming a GPU effectively to process smart meter data, and demonstrate experimentally that this choice of implementation enables substantial improvements in terms of both running time and energy-efficiency as compared to the multi-core CPU.
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 | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
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".