Utilizing physics-based input features within a machine learning model to predict wind speed forecasting error
-
Published:2021-03-01
Issue:1
Volume:6
Page:295-309
-
ISSN:2366-7451
-
Container-title:Wind Energy Science
-
language:en
-
Short-container-title:Wind Energ. Sci.
Author:
Vassallo Daniel, Krishnamurthy RaghavendraORCID, Fernando Harindra J. S.
Abstract
Abstract. Machine learning is quickly becoming a commonly used technique for wind speed and power forecasting. Many machine learning methods utilize exogenous variables as input features, but there remains the question of which atmospheric variables are most beneficial for forecasting, especially in handling non-linearities that lead to forecasting error. This question is addressed via creation of a hybrid model that utilizes an autoregressive integrated moving-average (ARIMA) model to make an initial wind speed forecast followed by a random forest model that attempts to predict the ARIMA forecasting error using knowledge of exogenous atmospheric variables.
Variables conveying information about atmospheric stability and turbulence as well as inertial forcing are found to be useful in dealing with non-linear error prediction. Streamwise wind speed, time of day, turbulence intensity, turbulent heat flux, vertical velocity, and wind direction are found to be particularly useful when used in unison for hourly and 3 h timescales. The prediction accuracy of the developed ARIMA–random forest hybrid model is compared to that of the persistence and bias-corrected ARIMA models. The ARIMA–random forest model is shown to improve upon the latter commonly employed modeling methods, reducing hourly forecasting error by up to 5 % below that of the bias-corrected ARIMA model and achieving an R2 value of 0.84 with true wind speed.
Funder
University of Notre Dame National Science Foundation
Publisher
Copernicus GmbH
Subject
Energy Engineering and Power Technology,Renewable Energy, Sustainability and the Environment
Reference48 articles.
1. Akish, E., Bianco, L., Djalalova, I. V., Wilczak, J. M., Olson, J. B.,
Freedman, J., Finley, C., and Cline, J.: Measuring the impact of additional
instrumentation on the skill of numerical weather prediction models at
forecasting wind ramp events during the first Wind Forecast Improvement
Project (WFIP), Wind Energy, 22.9, 1165–1174, 2019. a 2. Bianco, L., Djalalova, I. V., Wilczak, J. M., Olson, J. B., Kenyon, J. S., Choukulkar, A., Berg, L. K., Fernando, H. J. S., Grimit, E. P., Krishnamurthy, R., Lundquist, J. K., Muradyan, P., Pekour, M., Pichugina, Y., Stoelinga, M. T., and Turner, D. D.: Impact of model improvements on 80 m wind speeds during the second Wind Forecast Improvement Project (WFIP2), Geosci. Model Dev., 12, 4803–4821, https://doi.org/10.5194/gmd-12-4803-2019, 2019. a 3. Bodini, N., Lundquist, J. K., and Optis, M.: Can machine learning improve the model representation of turbulent kinetic energy dissipation rate in the boundary layer for complex terrain?, Geosci. Model Dev., 13, 4271–4285, https://doi.org/10.5194/gmd-13-4271-2020, 2020. a, b 4. Box, G. E., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M.: Time series
analysis: forecasting and control, John Wiley & Sons, Hoboken, NJ, 2015. a 5. Breiman, L.: Random forests, Mach. Learn., 45, 5–32, 2001. a
Cited by
13 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|