# A Comprehensive Wind Power Forecasting System Integrating Artificial Intelligence and Numerical Weather Prediction

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Numerical Weather Prediction

^{−1}in the first few hours. After 15 h, the MAE values cluster around 1.8 ms

^{−1}for all the three models. These results suggest WRF RTFDDA provides value beyond the coarser operational models out to 15 h.

## 3. Statistical Postprocessing

## 4. Probabilistic Prediction

^{−1}), and ${o}_{n}$ is the categorical observation (0 if the event does not occur and 1 if it does occur). A lower value of the Brier score indicates better performance, with 0 corresponding to a perfect forecast. Using the DICast forecast as a reference, the Brier skill score (BSS) is calculated as:

_{DICast}is the BS of DICast. In the case of DICast, p

_{n}in (2) can only take 1 or 0 values, e.g., if the forecasted wind speed is greater or lower than 10 ms

^{−1}, respectively. The BSS represents the measure of the probabilistic forecast performance in comparison to the reference forecast and measures the ability of the model to issue a better probabilistic forecast than the reference. Positive (negative) values of BSS indicate better (worse) performances of AnEn than DICast.

## 5. Short-range Forecasting

## 6. Predicting Extreme Weather

#### 6.1. Input Forecasts

#### 6.2. Forecasts

#### 6.3. Wind and Temperature Forecasts

#### 6.4. Turbine Forecasts

#### 6.5. Case Study

## 7. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Mahoney, W.P.; Parks, K.; Wiener, G.; Liu, Y.; Myers, W.L.; Sun, J.; Monache, L.D.; Hopson, T.; Johnson, D.; Haupt, S.E. A Wind Power Forecasting System to Optimize Grid Integration. IEEE Trans. Sustain. Energy
**2012**, 3, 670–682. [Google Scholar] [CrossRef] - Haupt, S.E.; Mahoney, W.P.; Parks, K. Wind Power Forecasting; Springer Science and Business Media LLC: New York, NY, USA, 2014; pp. 295–318. [Google Scholar]
- Haupt, S.E.; Mahoney, W.P.; Parks, K. Wind Power Forecasting. Weather Matters Energy
**2014**, 295–318. [Google Scholar] - Giebel, G.; Kariniotakis, G. Best Practice in Short-term Forecasting—A Users Guide. In Proceedings of the European Wind Energy Conference and Exhibition, Milan, Italy, 7–10 May 2007. [Google Scholar]
- Monteiro, C.; Bessa, R.; Miranda, V.; Botterud, A.; Wang, J.; Conzelmann, G.; Porto, I. Wind power forecasting: State-of-the-art 2009. In Proceedings of the Argonne National Laboratory, Argonne, IL, USA, 20 November 2009. [Google Scholar]
- Ahlstrom Jone, L.; Zavadil, R.; Grant, W. The future of wind forecasting and utility operations. IEEE Power Energy Mag.
**2005**, 3, 57–64. [Google Scholar] [CrossRef] - Wilczak, J.; Finley, C.; Freedman, J.; Cline, J.; Bianco, L.; Olson, J.; Djalalova, I.; Sheridan, L.; Ahlstrom, M.; Manobianco, J.; et al. The Wind Forecast Improvement Project (WFIP): A Public-Private Partnership Addressing Wind Energy Forecast Needs. Bull. Am. Meteorol. Soc.
**2015**, 96, 1699–1718. [Google Scholar] [CrossRef] - Gneiting, T.; Larson, K.; Westrick, K.; Genton, M.G.; Aldrich, E. Calibrated Probabilistic Forecasting at the Stateline Wind Energy Center. J. Am. Stat. Assoc.
**2006**, 101, 968–979. [Google Scholar] [CrossRef] - Ding, Y. Data Science for Wind Energy, 1st ed.; CRC: Boca Raton, FL, USA, 2019; p. 424. [Google Scholar]
- Skamarock, W.C.; Klemp, J.B.; Dudhia, J.; Gill, D.O.; Barker, D.M.; Duda, M.G.; Huang, X.-Y.; Wang, W.; Powers, J.G. A Description of the Advanced Research WRF Version 3; NCAR Tech Note NCAR/TN 475 STR; National Center for Atmospheric Research: Boulder, CO, USA, 2008; p. 125. [Google Scholar]
- Benjamin, S.G.; Weygandt, S.S.; Brown, J.M.; Hu, M.; Alexander, C.; Smirnova, T.G.; Olson, J.B.; James, E.; Dowell, D.C.; Grell, G.A.; et al. A North American Hourly Assimilation and Model Forecast Cycle: The Rapid Refresh. Mon. Weather. Rev.
**2016**, 144, 1669–1694. [Google Scholar] [CrossRef] - Liu, Y.; Warner, T.; Swerdlin, S.; Betancourt, T.; Knievel, J.; Mahoney, B.; Pace, J.; Rostkier-Edelstein, D.; Jacobs, N.A.; Childs, P.; et al. NCAR ensemble RTFDDA: Real-time operational forecasting applications and new data assimilation developments. In Proceedings of the 24th Conference on Weather Analysis and Forecasting and the 20th Conference on Numerical Weather Prediction, Seattle, WA, USA, 11–15 January 2011. [Google Scholar]
- Antoniou, I.; Pedersen, T.F. Nacelle Anemometry on a 1 MW Wind Turbine: Comparing the Power Performance Results by Use of the Nacelle or Mast Anemometer; Risø Report Risø-R-941(EN); Forskningscenter Risø: Roskilde, Denmark, 1997; p. 34. [Google Scholar]
- Smith, B.; Link, H.; Randall, G.; McCoy, T. Applicability of Nacelle Anemometer Measurements for Use in Turbine Power Performance Tests; National Renewable Energy Laboratory preprint NREL/CP-500-32494; National Renewable Energy Laboratory: Golden, CO, USA, 2002. [Google Scholar]
- Cheng, W.Y.; Liu, Y.; Bourgeois, A.J.; Wu, Y.; Haupt, S.E. Short-term wind forecast of a data assimilation/weather forecasting system with wind turbine anemometer measurement assimilation. Renew. Energy
**2017**, 107, 340–351. [Google Scholar] [CrossRef] - Myers, W.; Wiener, G.; Linden, S.; Haupt, S.E. A consensus forecasting approach for improved turbine hub height wind speed predictions. In Proceedings of the WindPower 2011, Anaheim, CA, USA, 24 May 2011. [Google Scholar]
- Gneiting, T.; Katzfuss, M. Probabilistic Forecasting. Annu. Rev. Stat. Its Appl.
**2014**, 1, 125–151. [Google Scholar] [CrossRef] - Monache, L.D.; Eckel, F.A.; Rife, D.L.; Nagarajan, B.; Searight, K. Probabilistic Weather Prediction with an Analog Ensemble. Mon. Weather Rev.
**2013**, 141, 3498–3516. [Google Scholar] [CrossRef][Green Version] - Alessandrini, S.; Monache, L.D.; Sperati, S.; Nissen, J. A novel application of an analog ensemble for short-term wind power forecasting. Renew. Energy
**2015**, 76, 768–781. [Google Scholar] [CrossRef] - Ezzat, A.A.; Jun, M.; Ding, Y. Spatio-temporal short-term wind forecast: A calibrated regime-switching method. Ann. Appl. Stat.
**2019**, 13, 1484–1510. [Google Scholar] [CrossRef] - Junk, C.; Delle Monache, L.; Alessandrini, S.; Cervone, G.; von Bremen, L. Predictor-weighting strategies for probabilistic wind power forecasting with an analog ensemble. Meteorol. Z.
**2015**, 24, 361–379. [Google Scholar] [CrossRef] - Sun, J.; Crook, N.A. Dynamical and Microphysical Retrieval from Doppler Radar Observations Using a Cloud Model and Its Adjoint. Part I: Model Development and Simulated Data Experiments. J. Atmos. Sci.
**1997**, 54, 1642–1661. [Google Scholar] [CrossRef] - Sun, J.; Chen, M.; Wang, Y. A Frequent-Updating Analysis System Based on Radar, Surface, and Mesoscale Model Data for the Beijing 2008 Forecast Demonstration Project. Weather. Forecast.
**2010**, 25, 1715–1735. [Google Scholar] [CrossRef] - Bernstein, B.C.; McDonough, F.; Politovich, M.K.; Brown, B.G.; Ratvasky, T.P.; Miller, D.R.; Wolff, C.A.; Cunning, G. Current Icing Potential: Algorithm Description and Comparison with Aircraft Observations. J. Appl. Meteorol.
**2005**, 44, 969–986. [Google Scholar] [CrossRef] - McDonough, F.; Bernstein, B.C.; Politovich, M.K.; Wolff, C.A. The forecast icing potential (FIP) algorithm, Preprints. In Proceedings of the 20th International Conference on Interactive Information and Processing Systems (IIPS) for Meteorology, Oceanography, and Hydrology, Seattle, WA, USA, 14 January 2004. [Google Scholar]
- Thompson, G.; Field, P.; Rasmussen, R.M.; Hall, W.D. Explicit Forecasts of Winter Precipitation Using an Improved Bulk Microphysics Scheme. Part II: Implementation of a New Snow Parameterization. Mon. Weather. Rev.
**2008**, 136, 5095–5115. [Google Scholar] [CrossRef] - Kosovic, B.; Haupt, S.E.; Wiener, G.; Delle Monache, L.; Liu, Y.; Linden, S.; Politovich, M.; Sun, J. Scientific Advances in Wind Power Forecasting. In Proceedings of the American Wind Energy Association, Orlando, FL, USA, 21 May 2015. [Google Scholar]

**Figure 1.**Flowchart of the National Center for Atmospheric Research’s (NCAR’s) Xcel Energy power prediction system. NCEP: U.S. National Centers for Environmental Prediction, NAM: North American model, GFS: global forecasting system, RUC: Rapid Update Cycle, GEM Global Environmental Multiscale model, WRF RTFDDA: Weather Research and Forecasting-based real-time four-dimensional data assimilation, and VDRAS: variational doppler radar analysis system.

**Figure 2.**Comparison of hourly data assimilation and forecasting cycles without (

**left panel**) and with (

**right panel**) assimilation of wind turbine hub-height wind speed observations for a large wind farm in Northern Colorado. The black lines show the mean wind. Different color lines represent forecasts from different cycles with the first (last) two digits in the legend denoting the day of the month (hour in UTC). Conventional obs DA: conventional observation data assimilation and farm ws DA: farm wind speed data assimilation.

**Figure 3.**Comparison of the performance of RTFDDA with baseline numerical weather prediction (NWP) models. MAE: mean absolute error.

**Figure 5.**Example of an analog ensemble forecast probability density function (PDF) over one station of the dataset. The blue shadings correspond to the 25–75 (

**darker**) and 5–95 (

**lighter**) quantiles. The black and yellow dashed lines represent the wind speed observations and AnEn ensemble mean, respectively. The red line is the DICast wind speed forecast. AnEn: analog ensemble.

**Figure 6.**Root mean square error (RMSE) as a function of forecast lead time for DICast (

**red**) and AnEn means (

**black**) computed over all stations. Bootstrap 5%–95% confidence intervals are plotted for AnEn only. RMSE values listed are computed by including all lead times.

**Figure 7.**Brier skill score (BSS) of the analog ensemble (AnEn) with DICast as a reference, as a function of forecast lead time, computed over all the stations. The BSS 5%–95% bootstrap confidence intervals are also shown. The event considered is wind speed greater than 10 ms

^{−1}.

**Figure 8.**Schematic of the observations-based expert system for short-term forecasting. Available wind speed observations at 10 m in concentric circles around a wind farm are used to calculate the wind ramp metric, which is then used to compute changes in power production.

**Figure 9.**Summary schematic visualizing the various input datasets to the extreme weather system (ExWx). For DICast, C1-C4 indicate various configurations of the DICast forecast that are dependent on the input model data available at that lead time.

**Figure 10.**Curves representing the interest in icing conditions (0–1) for three variables from the WRF RTFDDA model data. Top panel is height of the model level, middle panel represents supercooled liquid water, (i.e., liquid rain or cloud drops below freezing), and the bottom panel shows temperature. The intersection of the three curves where they return a value of 1 will maximize the icing potential from the WRF RTFDDA model data. SLW: supercooled liquid water.

**Figure 11.**Forecasts of icing potential, combined from all turbines on a single farm, from 57 consecutive runs of the extreme weather system (y-axis). The first run shown is the 2000 UTC forecast from the extreme weather system on 24 December, 2014. Black shading indicates valid times within the event window (2000 UTC on 25 December–0400 UTC on 26 December) with an icing potential forecast of < 0.5, light blue shading indicates an icing potential forecast of > 0.5 within the event window, orange shading indicates an icing potential forecast of > 0.5 outside the event window, and gray shading indicates an icing potential forecast of < 0.5 outside the event window. Vertical lines indicate the division between C1, C2, and C3 DICast forecast system data (see Figure 9).

**Figure 12.**Wind speed weighted metric to identify periods when power production was less than expected and wind speeds were high enough to have confidence in the manufacturer’s power curve (i.e., not in the lower tail of the curve). The red line shows the farm average, while the black dashed lines show +/- the standard deviation for the farm. Top panel is for 25 December 2014, and bottom panel is for 26 December 2014. Higher values indicate a higher likelihood of icing (or curtailment).

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Kosovic, B.; Haupt, S.E.; Adriaansen, D.; Alessandrini, S.; Wiener, G.; Delle Monache, L.; Liu, Y.; Linden, S.; Jensen, T.; Cheng, W.; Politovich, M.; Prestopnik, P. A Comprehensive Wind Power Forecasting System Integrating Artificial Intelligence and Numerical Weather Prediction. *Energies* **2020**, *13*, 1372.
https://doi.org/10.3390/en13061372

**AMA Style**

Kosovic B, Haupt SE, Adriaansen D, Alessandrini S, Wiener G, Delle Monache L, Liu Y, Linden S, Jensen T, Cheng W, Politovich M, Prestopnik P. A Comprehensive Wind Power Forecasting System Integrating Artificial Intelligence and Numerical Weather Prediction. *Energies*. 2020; 13(6):1372.
https://doi.org/10.3390/en13061372

**Chicago/Turabian Style**

Kosovic, Branko, Sue Ellen Haupt, Daniel Adriaansen, Stefano Alessandrini, Gerry Wiener, Luca Delle Monache, Yubao Liu, Seth Linden, Tara Jensen, William Cheng, Marcia Politovich, and Paul Prestopnik. 2020. "A Comprehensive Wind Power Forecasting System Integrating Artificial Intelligence and Numerical Weather Prediction" *Energies* 13, no. 6: 1372.
https://doi.org/10.3390/en13061372