Institutional Repository of Vilnius University
Mašininio mokymo ir statistinių metodų taikymas saulės elektros gamybos monitoringo sistemose /
Abstract
dc:descriptionThis thesis investigates and implements the application of machine learning and statistical methods in solar power monitoring systems. The work focuses on automated data labeling and classification, heatmap-based visualization, and performance ratio (PR) calculation. A unified tagging system was developed to standardize measurement data across different solar plants. The classification model, based on natural language processing and machine learning, achieved over 99.7% accuracy. An interactive heatmap visualization was created to analyze string-level inverter performance and detect failures in real time. Additionally, a PR computation system was implemented using real data and modeled irradiance, evaluation of tilted irradiance models accuracy (MAE = 0,119, RMSE = 0,154) and their suitability for PR estimation was conducted. Results demonstrate that automated methods can significantly enhance monitoring efficiency, analytical accuracy, and solar plant maintenance.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Voveris, Lukas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD239028941&prefLang=en_US