Analyzing predictive ability of artificial neural network–based short-term forecasting algorithms for temperature and wind speed

Sunglee, J.A.; Beeharry, Yogesh

doi:10.1016/b978-0-323-90396-7.00008-0

Cited by 1 publication

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the datasets referenced by the authors in the reviewed articles, many either do not specify where the data can be accessed or obtained, or they simply mention that they do not have permission to share the data. However, Piazza et al, 2021 [46] states that the data used were retrieved from a publicly available database published by the U.S. National Renewable Energy Laboratory (NREL), Sunglee et al, 2022, obtained data from AccuWeather [40], Bentsen et al, 2023 [39] downloaded the data using the Frost API and Tagliaferri et al, 2015 [27] acquired the data from America's Cup Event Authority.…”

Section: Time Resolution and General Resultsmentioning

confidence: 99%

“…Using a resolution of 10 min [32][33][34][35][36][37][38][39], it was possible to predict wind characteristics up to 1008 steps [37], which is equivalent to one week. Sunglee et al [40] utilized highresolution 5-s wind data to realize 20 min resolution predictions up to one hour ahead. Furthermore, using an interval of 1 h steps [41][42][43][44][45][46][47][48][49] it was possible to forecast a maximum range of one week [42].…”

Section: Nowcasting Resolution and Range Distributionmentioning

confidence: 99%

“…The data available were further compiled, grouping the results according to the model. The most used machine learning approach was FFNN, representing eight of the analyzed articles [32,34,36,40,41,43,44,49]. The second most published approach, with three articles [30,31,38], was LSTM, and the remaining eleven studies were dispersed over a variety of models, therefore grouped as "other" [27][28][29]33,35,37,39,42,[45][46][47][48].…”

Section: Assessment Of Frequently Employed Modelsmentioning

confidence: 99%

See 2 more Smart Citations

The Potential of Machine Learning for Wind Speed and Direction Short-Term Forecasting: A Systematic Review

Alves,

Mendonça,

Mostafa

et al. 2023

Computers

View full text Add to dashboard Cite

Wind forecasting, which is essential for numerous services and safety, has significantly improved in accuracy due to machine learning advancements. This study reviews 23 articles from 1983 to 2023 on machine learning for wind speed and direction nowcasting. The wind prediction ranged from 1 min to 1 week, with more articles at lower temporal resolutions. Most works employed neural networks, focusing recently on deep learning models. Among the reported performance metrics, the most prevalent were mean absolute error, mean squared error, and mean absolute percentage error. Considering these metrics, the mean performance of the examined works was 0.56 m/s, 1.10 m/s, and 6.72%, respectively. The results underscore the novel effectiveness of machine learning in predicting wind conditions using high-resolution time data and demonstrated that deep learning models surpassed traditional methods, improving the accuracy of wind speed and direction forecasts. Moreover, it was found that the inclusion of non-wind weather variables does not benefit the model’s overall performance. Further studies are recommended to predict both wind speed and direction using diverse spatial data points, and high-resolution data are recommended along with the usage of deep learning models.

show abstract

Section: Time Resolution and General Resultsmentioning

confidence: 99%