Data-Driven Estimation of Soiling Loss and Optimal Cleaning Schedule for a Utility-Scale PV Plant
Bibliographic record
Abstract
Soiling of panels in solar power plants can reduce production levels. In this thesis, we estimate the effect of soiling on power production and efficiency, as well as the gains from cleaning. Power data from a plant in southwest India was recorded every 5 minutes spanning 6 months. We analyzed this data to estimate efficiency degradation rates resulting from accumulation of soil and dust. The major challenge was filtering dataset noise/anomalies due to variations in micro-weather conditions. The key contribution of the thesis is a data-driven cleaning schedule algorithm. The algorithm detects cleaning events and produces a segmentation of the timeline into cleaning and soiling intervals. From the cleaning intervals we estimate the gains from panel cleaning, and from the soiling intervals we calculate the rate of power/efficiency loss. We apply these results to solve optimization problems regarding the cleaning schedule of a solar power plant. For example, by comparing the cost of cleaning against the potential gains in power production, we answer the questions “Which panel should I clean first/on this day?” and “Which day should I clean all panels?”. We hope that the contributions of this research will provide important insights for any party working with solar power data.
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) | 0.000 | 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".