Integrated deep learning and image processing method for modeling energy loss due to shadows in solar arrays
Bibliographic record
Abstract
Shading poses a serious challenge to photovoltaic (PV) systems power generation, causing energy losses of up to 40 %, leading to power mismatches, hotspot formation, and accelerated module degradation. Accurate modelling and simulation of shading are critical for improving photovoltaic (PV) performance. This study develops two shadow‑detection pipelines: (i) the Classic Hough Transform (CHT) combined with K‑means segmentation and (ii) a new Deep Hough Transform (DHT) that learns semantic line features without the need for PV‑specific training data. A 1-kilowatt capacity solar array with planned shading devices was developed and used to perform the experimental analysis. The proposed methodology achieved an accuracy of 0.85, indicating a 32.81 % improvement in solar array detection compared to CHT methods. Computed energy losses due to shading were within 0.5 % to 1.9 % of System Advisor Model (SAM’s) simulated losses. Evaluation with transient shadows from a pedestrian, vehicle, and cloud showed an average mIoU of 81.8 % highlighting the methods advantage over existing 3D modeling-based simulation software. Statistical analysis confirmed the method’s consistency, yielding Dice = 0.857 (95 % CI 0.728–0.943) and mIoU = 0.771 (CI 0.595–0.893). The parametric analysis highlighted the time of day and number of obstructions as key factors influencing shading on solar arrays, with mornings and evenings experiencing over 6 % shading loss variations. Overall, this integrated approach develops robust, real-time modelling and simulation for optimizing large solar energy systems.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".