SOLETE-1.0.zip (15.53 kB)
Download fileThe SOLETE platform
Author: Daniel Vázquez Pombo (dvapo@elektro.dtu.dk), ORCID: https://orcid.org/0000-0001-5664-9421
-------------------------------------------------------------------------------
This item is Machine Learning platform aimed at machine learning forecasting of time series focused on PV power. The code is disclosed to increase the transparency and replicability of [1] and [2] which are still under review.
The different scripts have various functions. One allows to import SOLETE and show some plots. Another is a platform where you can play with different Machine Learning models for time series forecasting. The application focuses on predicting PV power, but it can be easily edited by the user.
For more information, dependencies, etc. Refer to the git.
The platform should be useful as a learning tool in the machine learning field.
The SOLETE dataset (currently a small sample, the full length will be released upon acceptance of the related papers): https://doi.org/10.11583/DTU.17040767
SOLETE includes 15 months of 5 minute and hourly measurements from the 1st June 2018 to 1st September 2019 covering: Timestamp, air temperature, relative humidity, pressure, wind speed, wind direction, global horizontal irradiance, plane of array irradiance, and active power recorded from an 11 kW Gaia wind turbine and a 10 kW PV inverter.
The origin of the data is SYSLAB, part of DTU Elektro. If you want to learn more about the dataset, you should check out [3].
The publications related to this item are:
[1] D. V. Pombo, H. W. Bindner, S. V. Spataru, P. E. Sørensen, P. Bacher, Increasing the Accuracy of Hourly Multi-Output Solar Power Forecast with Physics-Informed Machine Learning, Sensors 22 (3) (2022) 749.
[2] D.V. Pombo, P. Bacher, C. Ziras, H.W. Bindner, S.V. Spataru, P. Sørensen, Benchmarking Physics-Informed Machine Learning-based Short Term PV-Power Forecasting Tools, Under Review.
[3] D.V. Pombo, O.G. Gehrke, H.W. Bindner, SOLETE, a 15-month long holistic dataset including: meteorology, co-located wind and solar PV power from Denmark with various resolutions, Data in Brief. In Press.