Photovoltaic (PV) Generation Dataset with Orientation Diversity
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This dataset contains hourly photovoltaic (PV) generation data and associated input variables collected from an experimental rooftop PV system. The dataset includes temporal, meteorological, and orientation-related features used for short-term PV power forecasting. Measurements were recorded at an hourly resolution over approximately one year (7080 hours). The dataset consists of the following variables: - Day: Day of the year - Cosine of Day: Cyclical representation of the day of the year - Hour: Hour of the day - Cosine of Hour: Cyclical representation of the hour of the day - Air Temperature (°C) - Dew Point (°C) - Wind Speed (m/s) - Air Pressure (hPa) - Weather Condition: Categorical weather description - Solar Radiation (W/m²) For each PV panel (PV-1 to PV-5), the following variables are provided: - Cosine value of the solar incidence angle - Measured PV power output (W or Wh) Additionally: - Total PV Power: Aggregated power output of all panels The PV system consists of multiple panels with different tilt and azimuth configurations, enabling the analysis of orientation-aware PV forecasting under identical environmental conditions. This repository includes raw and processed data along with variable descriptions to support reproducible research in photovoltaic forecasting and energy systems. ## CitationIf you use this dataset in academic work, please cite: "Short-term forecasting of rooftop photovoltaic energy generation using machine learning techniques", PeerJ Computer Science. ## LicenseThis dataset is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.
Fields of Study & Subjects
Solar Radiation and Photovoltaics
Photovoltaic System Optimization Techniques
Energy Load and Power Forecasting
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 27 March 2026
- Language
- EN
- Document type
- Dataset