In Global challenges (Hoboken, NJ)
Machine learning is arising as a major solution for the photovoltaic (PV) power prediction. Despite the abundant literature, the effect of climate on yield predictions using machine learning is unknown. This work aims to find climatic trends by predicting the power of 48 PV systems around the world, equally divided into four climates. An extensive data gathering process is performed and open-data sources are prioritized. A website www.tudelft.nl/open-source-pv-power-databases has been created with all found open data sources for future research. Five machine learning algorithms and a baseline one have been trained for each PV system. Results show that the performance ranking of the algorithms is independent of climate. Systems in dry climates depict on average the lowest Normalized Root Mean Squared Error (NRMSE) of 47.6 %, while those in tropical present the highest of 60.2 %. In mild and continental climates the NRMSE is 51.6 % and 54.5 %, respectively. When using a model trained in one climate to predict the power of a system located in another climate, on average systems located in cold climates show a lower generalization error, with an additional NRMSE as low as 5.6 % depending on the climate of the test set. Robustness evaluations were also conducted that increase the validity of the results.
Alcañiz Alba, Lindfors Anders V, Zeman Miro, Ziar Hesan, Isabella Olindo
2023-Jan
Köppen‐Geiger, climate, forecasting, machine learning, photovoltaics
