Performance Evaluation of Neural Network-Based Short-Term Solar Irradiation Forecasts

Simon Liebermann, Jung-Sup Um, YoungSeok Hwang and Stephan Schlüter
Additional contact information
Simon Liebermann: Department of Mathematics and Economics, University of Ulm, 89069 Ulm, Germany
Jung-Sup Um: Department of Geography, Kyungpook National University, Daegu 41566, Korea
YoungSeok Hwang: Department of Climate Change, Kyungpook National University, Daegu 41566, Korea
Stephan Schlüter: Department of Mathematics, Natural and Economic Sciences, University of Applied Sciences Ulm, 89075 Ulm, Germany

Energies, 2021, vol. 14, issue 11, 1-21

Abstract: Due to the globally increasing share of renewable energy sources like wind and solar power, precise forecasts for weather data are becoming more and more important. To compute such forecasts numerous authors apply neural networks (NN), whereby models became ever more complex recently. Using solar irradiation as an example, we verify if this additional complexity is required in terms of forecasting precision. Different NN models, namely the long-short term (LSTM) neural network, a convolutional neural network (CNN), and combinations of both are benchmarked against each other. The naive forecast is included as a baseline. Various locations across Europe are tested to analyze the models’ performance under different climate conditions. Forecasts up to 24 h in advance are generated and compared using different goodness of fit (GoF) measures. Besides, errors are analyzed in the time domain. As expected, the error of all models increases with rising forecasting horizon. Over all test stations it shows that combining an LSTM network with a CNN yields the best performance. However, regarding the chosen GoF measures, differences to the alternative approaches are fairly small. The hybrid model’s advantage lies not in the improved GoF but in its versatility: contrary to an LSTM or a CNN, it produces good results under all tested weather conditions.

Keywords: neural network; solar irradiation; time series forecasting; LSTM; CNN; C45; C53; C58 (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
https://www.mdpi.com/1996-1073/14/11/3030/pdf (application/pdf)
https://www.mdpi.com/1996-1073/14/11/3030/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:14:y:2021:i:11:p:3030-:d:560922

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().