# Wind Turbine Noise Prediction Using Random Forest Regression

^{*}

## Abstract

**:**

## 1. Introduction

#### Recent Researches on the Subject

## 2. Methodology

- Solo 01 dB integrating sound level meter model of “Class 1”
- Larson Davis CAL 200 Calibrator
- Tripod
- Windproof headphones

- WEC1Ac: Active power (kW) measured at Wind Turbine 1
- WEC1WS: Wind speed (m/s) measured at nacelle of the Wind Turbine 1
- WEC2Ac: Active power (kW) measured at Wind Turbine 2
- WEC2WS: Wind speed (m/s) measured at nacelle of the Wind Turbine 2
- WEC3Ac: Active power (kW) measured at Wind Turbine 3
- WEC3WS: Wind speed (m/s) measured at nacelle of the Wind Turbine 3
- WEC4Ac: Active power (kW) measured at Wind Turbine 4
- WEC4WS: Wind speed (m/s) measured at nacelle of the Wind Turbine 4

## 3. Results

#### 3.1. Acoustic Measurements and SCADA Data Analysis

#### 3.2. Data Processing

#### 3.3. Linear Regression Analysis

#### 3.4. Random Forest Model

## 4. Discussion

## 5. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Owusu, P.A.; Asumadu-Sarkodie, S. A review of renewable energy sources, sustainability issues and climate change mitigation. Cogent Eng.
**2016**, 3, 1167990. [Google Scholar] [CrossRef] - Samorani, M. The wind farm layout optimization problem. In Handbook of Wind Power Systems; Springer: Berlin/Heidelberg, Germany, 2013; pp. 21–38. [Google Scholar]
- Atlante Eolico. Interattivo Italiano. Available online: http://atlanteeolico.rse-web.it/ (accessed on 5 November 2019).
- Szychowska, M.; Hafke-Dys, H.; Preis, A.; Kociński, J.; Kleka, P. The influence of audio-visual interactions on the annoyance ratings for wind turbines. Appl. Acoust.
**2018**, 129, 190–203. [Google Scholar] [CrossRef] - Davy, J.L.; Burgemeister, K.; Hillman, D. Wind turbine sound limits: Current status and recommendations based on mitigating noise annoyance. Appl. Acoust.
**2018**, 140, 288–295. [Google Scholar] [CrossRef] - Lee, G.S.; Cheong, C.; Shin, S.H.; Jung, S.S. A case study of localization and identification of noise sources from a pitch and a stall regulated wind turbine. Appl. Acoust.
**2012**, 73, 817–827. [Google Scholar] [CrossRef] - Pedersen, E.; Waye, K.P. Wind turbine noise, annoyance and self-reported health and well-being in different living environments. Occup. Environ. Med.
**2007**, 64, 480–486. [Google Scholar] [CrossRef][Green Version] - Doolan, C. A review of wind turbine noise perception, annoyance and low frequency emission. Wind Eng.
**2013**, 37, 97–104. [Google Scholar] [CrossRef] - Spera, D.A. Wind Turbine Technology; ASME Press: New York, NY, USA, 1994. [Google Scholar]
- Jha, A.R. Wind Turbine Technology; CRC Press: Boca Raton, FL, USA, 2010. [Google Scholar]
- Echavarria, E.; Hahn, B.; Van Bussel, G.J.; Tomiyama, T. Reliability of wind turbine technology through time. J. Sol. Energy Eng.
**2008**, 130, 031005. [Google Scholar] [CrossRef] - Guarnaccia, C.; Mastorakis, N.E.; Quartieri, J. A mathematical approach for wind turbine noise propagation. In Proceedings of the Mathematics and Computer Engineering, American Conference of Applied Mathematics (AMERICAN-MATH’11), Puerto Morelos, Mexico, 29 January 2011; pp. 187–194. [Google Scholar]
- Forssén, J.; Schiff, M.; Pedersen, E.; Waye, K.P. Wind turbine noise propagation over flat ground: Measurements and predictions. Acta Acust. United Acust.
**2010**, 96, 753–760. [Google Scholar] [CrossRef] - Son, E.; Kim, H.; Kim, H.; Choi, W.; Lee, S. Integrated numerical method for the prediction of wind turbine noise and the long range propagation. Curr. Appl. Phys.
**2010**, 10, S316–S319. [Google Scholar] [CrossRef] - Barlas, E.; Zhu, W.J.; Shen, W.Z.; Dag, K.O.; Moriarty, P. Consistent modelling of wind turbine noise propagation from source to receiver. J. Acoust. Soc. Am.
**2017**, 142, 3297–3310. [Google Scholar] [CrossRef][Green Version] - Sessarego, M.; Shen, W.Z.; Barlas, E. Wind turbine noise propagation in flat terrain for wind farm layout optimization frameworks. In Proceedings of the Eighth International Conference on Wind Turbine Noise, Lisbon, Portugal, 12–14 June 2019. [Google Scholar]
- Wan, C.; Xu, Z.; Pinson, P.; Dong, Z.Y.; Wong, K.P. Probabilistic forecasting of wind power generation using extreme learning machine. IEEE Trans. Power Syst.
**2013**, 29, 1033–1044. [Google Scholar] [CrossRef] - Foley, A.M.; Leahy, P.G.; Marvuglia, A.; McKeogh, E.J. Current methods and advances in forecasting of wind power generation. Renew. Energy
**2012**, 37, 1–8. [Google Scholar] [CrossRef][Green Version] - Marvuglia, A.; Messineo, A. Monitoring of wind farms’ power curves using machine learning techniques. Appl. Energy
**2012**, 98, 574–583. [Google Scholar] [CrossRef] - Colak, I.; Sagiroglu, S.; Yesilbudak, M. Data mining and wind power prediction: A literature review. Renew. Energy
**2012**, 46, 241–247. [Google Scholar] [CrossRef] - Heinermann, J.; Kramer, O. Machine learning ensembles for wind power prediction. Renew. Energy
**2016**, 89, 671–679. [Google Scholar] [CrossRef] - Wang, H.Z.; Li, G.Q.; Wang, G.B.; Peng, J.C.; Jiang, H.; Liu, Y.T. Deep learning based ensemble approach for probabilistic wind power forecasting. Appl. Energy
**2017**, 188, 56–70. [Google Scholar] [CrossRef] - Clifton, A.; Kilcher, L.; Lundquist, J.K.; Fleming, P. Using machine learning to predict wind turbine power output. Environ. Res. Lett.
**2013**, 8, 024009. [Google Scholar] [CrossRef] - Li, Z.; Ye, L.; Zhao, Y.; Song, X.; Teng, J.; Jin, J. Short-term wind power prediction based on extreme learning machine with error correction. Prot. Control Mod. Power Syst.
**2016**, 1, 1. [Google Scholar] [CrossRef] - Tang, B.; Song, T.; Li, F.; Deng, L. Fault diagnosis for a wind turbine transmission system based on manifold learning and Shannon wavelet support vector machine. Renew. Energy
**2014**, 62, 1–9. [Google Scholar] [CrossRef] - Laouti, N.; Sheibat-Othman, N.; Othman, S. Support vector machines for fault detection in wind turbines. IFAC Proc. Vol.
**2011**, 44, 7067–7072. [Google Scholar] [CrossRef] - Liu, W.Y.; Tang, B.P.; Han, J.G.; Lu, X.N.; Hu, N.N.; He, Z.Z. The structure healthy condition monitoring and fault diagnosis methods in wind turbines: A review. Renew. Sustain. Energy Rev.
**2015**, 44, 466–472. [Google Scholar] [CrossRef] - Santos, P.; Villa, L.; Reñones, A.; Bustillo, A.; Maudes, J. An SVM-based solution for fault detection in wind turbines. Sensors
**2015**, 15, 5627–5648. [Google Scholar] [CrossRef] [PubMed] - Kusiak, A.; Verma, A. A data-driven approach for monitoring blade pitch faults in wind turbines. IEEE Trans. Sustain. Energy
**2010**, 2, 87–96. [Google Scholar] [CrossRef] - Wang, L.; Zhang, Z.; Long, H.; Xu, J.; Liu, R. Wind turbine gearbox failure identification with deep neural networks. IEEE Trans. Ind. Inform.
**2016**, 13, 1360–1368. [Google Scholar] [CrossRef] - Chen, F.; Tang, B.; Chen, R. A novel fault diagnosis model for gearbox based on wavelet support vector machine with immune genetic algorithm. Measurement
**2013**, 46, 220–232. [Google Scholar] [CrossRef] - Salcedo-Sanz, S.; Pastor-Sánchez, A.; Prieto, L.; Blanco-Aguilera, A.; García-Herrera, R. Feature selection in wind speed prediction systems based on a hybrid coral reefs optimization–Extreme learning machine approach. Energy Convers. Manag.
**2014**, 87, 10–18. [Google Scholar] [CrossRef] - Hu, Q.; Zhang, R.; Zhou, Y. Transfer learning for short-term wind speed prediction with deep neural networks. Renew. Energy
**2016**, 85, 83–95. [Google Scholar] [CrossRef] - Zhou, J.; Shi, J.; Li, G. Fine tuning support vector machines for short-term wind speed forecasting. Energy Convers. Manag.
**2011**, 52, 1990–1998. [Google Scholar] [CrossRef] - Liu, H.; Tian, H.Q.; Li, Y.F. Four wind speed multi-step forecasting models using extreme learning machines and signal decomposing algorithms. Energy Convers. Manag.
**2015**, 100, 16–22. [Google Scholar] [CrossRef] - Salcedo-Sanz, S.; Ortiz-Garcı, E.G.; Pérez-Bellido, Á.M.; Portilla-Figueras, A.; Prieto, L. Short term wind speed prediction based on evolutionary support vector regression algorithms. Expert Syst. Appl.
**2011**, 38, 4052–4057. [Google Scholar] [CrossRef] - Guo, Z.; Zhao, W.; Lu, H.; Wang, J. Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model. Renew. Energy
**2012**, 37, 241–249. [Google Scholar] [CrossRef] - Adagha, O.; Levy, R.M.; Carpendale, S.; Gates, C.; Lindquist, M. Evaluation of a visual analytics decision support tool for wind farm placement planning in Alberta: Findings from a focus group study. Technol. Forecast. Soc. Chang.
**2017**, 117, 70–83. [Google Scholar] [CrossRef] - Iannace, G. Effects of noise from wind turbines inside home. Wind Eng.
**2016**, 40, 25–30. [Google Scholar] [CrossRef][Green Version] - Doolan, C.J.; Moreau, D.J. An on-demand simultaneous annoyance and indoor noise recording technique. Acoust. Aust.
**2013**, 41, 141–145. [Google Scholar] - International Electrotechnical Commission. Wind Turbines-Part 11: Acoustic Noise Measurement Techniques; International Electrotechnical Commission: Geneva, Switzerland, 2012. [Google Scholar]
- Daneels, A.; Salter, W. What is SCADA? In Proceedings of the International Conference on Accelerator and Large Experimental Physics Control Systems, Trieste, Italy, 4–8 October 1999. [Google Scholar]
- Tautz-Weinert, J.; Watson, S.J. Using SCADA data for wind turbine condition monitoring–a review. Iet Renew. Power Gener.
**2016**, 11, 382–394. [Google Scholar] [CrossRef] - Knudsen, T.; Bak, T.; Soltani, M. Prediction models for wind speed at turbine locations in a wind farm. Wind Energy
**2011**, 14, 877–894. [Google Scholar] [CrossRef][Green Version] - Breiman, L. Random forests. Mach. Learn.
**2001**, 45, 5–32. [Google Scholar] [CrossRef] - Biau, G. Analysis of a random forests model. J. Mach. Learn. Res.
**2012**, 13, 1063–1095. [Google Scholar] - Ciaburro, G. Regression Analysis with R: Design and Develop Statistical Nodes to Identify Unique Relationships within Data at Scale; Packt Publishing Ltd.: Birmingham, United Kingdom, 2018. [Google Scholar]
- Tanaka, S.; Shiraishi, B. Wind effects on noise propagation for complicated geographical and road configurations. Appl. Acoust.
**2008**, 69, 1038–1043. [Google Scholar] [CrossRef] - Gallo, P.; Fredianelli, L.; Palazzuoli, D.; Licitra, G.; Fidecaro, F. A procedure for the assessment of wind turbine noise. Appl. Acoust.
**2016**, 114, 213–217. [Google Scholar] [CrossRef] - Najeem, S.; Sanjana, M.C.; Latha, G.; Durai, P.E. Wind induced ambient noise modelling and comparison with field measurements in Arabian Sea. Appl. Acoust.
**2015**, 89, 101–106. [Google Scholar] [CrossRef] - Patro, S.; Sahu, K.K. Normalization: A preprocessing stage. arXiv
**2015**, arXiv:1503.06462. [Google Scholar] [CrossRef] - Darlington, R.B. Regression and Linear Models; McGraw-Hill: New York, NY, USA, 1990; pp. 292–293. [Google Scholar]
- Hothorn, T.; Everitt, B.S. A handbook of Statistical Analyses Using R; Chapman and Hall/CRC: Boca Raton, FL, USA, 2014. [Google Scholar]
- Liaw, A.; Wiener, M. Classification and regression by randomForest. R news
**2002**, 2, 18–22. [Google Scholar] - Wang, Z.; Wang, Y.; Zeng, R.; Srinivasan, R.S.; Ahrentzen, S. Random Forest based hourly building energy prediction. Energy Build.
**2018**, 171, 11–25. [Google Scholar] [CrossRef] - Kusiak, A.; Verma, A. A data-mining approach to monitoring wind turbines. IEEE Trans. Sustain. Energy
**2011**, 3, 150–157. [Google Scholar] [CrossRef] - Lahouar, A.; Slama, J.B.H. Hour-ahead wind power forecast based on random forests. Renew. Energy
**2017**, 109, 529–541. [Google Scholar] [CrossRef] - Romero, V.P.; Maffei, L.; Brambilla, G.; Ciaburro, G. Modelling the soundscape quality of urban waterfronts by artificial neural networks. Appl. Acoust.
**2016**, 111, 121–128. [Google Scholar] [CrossRef] - Ali, J.B.; Saidi, L.; Harrath, S.; Bechhoefer, E.; Benbouzid, M. Online automatic diagnosis of wind turbine bearings progressive degradations under real experimental conditions based on unsupervised machine learning. Appl. Acoust.
**2018**, 132, 167–181. [Google Scholar] - Sun, H.; Zi, Y.; He, Z. Wind turbine fault detection using multiwavelet denoising with the data-driven block threshold. Appl. Acoust.
**2014**, 77, 122–129. [Google Scholar] [CrossRef] - Granata, F.; Papirio, S.; Esposito, G.; Gargano, R.; de Marinis, G. Machine learning algorithms for the forecasting of wastewater quality indicators. Water
**2017**, 9, 105. [Google Scholar] [CrossRef] - Asm, S.; Chen, X.; Fedorov, V.; Christensen, A.N.; Riis, N.A.B.; Branner, K.; Dahl, A.B.; Paulsen, R.R. Wind Turbine Surface Damage Detection by Deep Learning Aided Drone Inspection Analysis. Energies
**2019**, 12, 676. [Google Scholar][Green Version] - Elasha, F.; Shanbr, S.; Li, X.; Mba, D. Prognosis of a Wind Turbine Gearbox Bearing Using Supervised Machine Learning. Sensors
**2019**, 19, 3092. [Google Scholar] [CrossRef] [PubMed] - Iannace, G.; Ciaburro, G.; Trematerra, A. Fault Diagnosis for UAV Blades Using Artificial Neural Network. Robotics
**2019**, 8, 59. [Google Scholar] [CrossRef] - Iannace, G.; Ciaburro, G.; Trematerra, A. Heating, Ventilation, and Air Conditioning (HVAC) Noise Detection in Open-Plan Offices Using Recursive Partitioning. Buildings
**2018**, 8, 169. [Google Scholar] [CrossRef] - Arcos Jiménez, A.; Gómez Muñoz, C.; García Márquez, F. Machine learning for wind turbine blades maintenance management. Energies
**2018**, 11, 13. [Google Scholar] [CrossRef] - Möllerström, E.; Ottermo, F.; Hylander, J.; Bernhoff, H. Noise emission of a 200 kW vertical axis wind turbine. Energies
**2016**, 9, 19. [Google Scholar] [CrossRef] - Botelho, A.; Arezes, P.; Bernardo, C.; Dias, H.; Pinto, L. Effect of wind farm noise on local residents’ decision to adopt mitigation measures. Int. J. Environ. Res. Public Health
**2017**, 14, 753. [Google Scholar] [CrossRef] - Ageborg Morsing, J.; Smith, M.; Ögren, M.; Thorsson, P.; Pedersen, E.; Forssén, J.; Persson Waye, K. Wind turbine noise and sleep: Pilot studies on the influence of noise characteristics. Int. J. Environ. Res. Public Health
**2018**, 15, 2573. [Google Scholar] [CrossRef] - Escaler, X.; Mebarki, T. Full-Scale Wind Turbine Vibration Signature Analysis. Machines
**2018**, 6, 63. [Google Scholar] [CrossRef] - Kazak, J.; van Hoof, J.; Szewranski, S. Challenges in the wind turbines location process in Central Europe–The use of spatial decision support systems. Renew. Sustain. Energy Rev.
**2017**, 76, 425–433. [Google Scholar] [CrossRef]

**Figure 1.**Map view of the wind farm with indication of the towers. All the towers are located at a height higher than that of the receiver. The distances between the towers and the receiver are as follows: 1 = 230 m., 2 = 250 m., 3 = 400 m., 4 = 780 m.

**Figure 2.**Equipment during the acoustic measurement process (on the left) and a view from the window of the house where it is clearly possible to identify one of the 4 turbines (on the right).

**Figure 3.**The algorithm requires each tree of a random forest to be trained using a different random subset of fixed cardinality generated from the set of data available. The forecasts obtained from the trees are collected and averaged, in this way, the result will be closer to the actual value.

**Figure 7.**Variables importance of the Random Forest Model predictors (WEC1Ac—Active power measured at Wind Turbine 1, WEC1WS—Wind speed measured at Wind Turbine 1, WEC2Ac—Active power measured at Wind Turbine 2, WEC2WS—Wind speed measured at Wind Turbine 2, WEC3Ac—Active power measured at Wind Turbine 3, WEC3WS—Wind speed measured at Wind Turbine 3, WEC4Ac—Active power measured at Wind Turbine 4, WEC4WS—Wind speed measured at Wind Turbine 4).

**Figure 8.**Actual versus predicted values for both the tested models (Multiple linear regression model at the left, Random Forest model at the right).

WT 1 | WT 2 | WT 3 | WT 4 | |||||
---|---|---|---|---|---|---|---|---|

Time Stamp | Active Power [kW] | Wind Speed [m/s] | Active Power [kW] | Wind Speed [m/s] | Active Power [kW] | Wind Speed [m/s] | Active Power [kW] | Wind Speed [m/s] |

01:20 | 2058.6 | 15.6 | 2058.1 | 16.1 | 2059.9 | 16.5 | 2058.6 | 16.2 |

01:30 | 2059.5 | 14.9 | 2057.9 | 15.8 | 2058.4 | 15.4 | 2059.2 | 15.3 |

01:40 | 2058.9 | 13.6 | 2054.9 | 14.0 | 2058.4 | 14.2 | 2058.1 | 14.5 |

01:50 | 2012.4 | 11.7 | 2040.5 | 12.4 | 2039.9 | 12.5 | 2049.5 | 12.2 |

02:00 | 1846.9 | 10.7 | 1938.3 | 11.3 | 1992.6 | 11.5 | 2044.4 | 12.0 |

02:10 | 1632.2 | 10.1 | 1800.7 | 10.9 | 1930.9 | 11.2 | 1634.5 | 9.9 |

02:20 | 1957.5 | 11.7 | 1794.3 | 11.0 | 1999.9 | 11.9 | 1854.1 | 10.9 |

02:30 | 1907.6 | 11.6 | 1981.6 | 12.4 | 1964.9 | 12.9 | 1642.1 | 10.7 |

02:40 | 2028.1 | 13.5 | 2050.7 | 14.9 | 2029.2 | 14.6 | 2050.2 | 14.7 |

02:50 | 2052.5 | 16.6 | 2052.8 | 18.6 | 2041.5 | 17.8 | 2053.1 | 17.0 |

03:00 | 2055.3 | 18.9 | 2052.0 | 18.7 | 2042.5 | 19.5 | 2052.2 | 19.6 |

03:10 | 2055.9 | 21.3 | 2048.9 | 21.3 | 2053.5 | 20.5 | 2048.5 | 21.6 |

03:20 | 2058.9 | 22.3 | 2044.1 | 22.4 | 1372.1 | 21.0 | 2052.5 | 22.3 |

WT 1 | WT 2 | WT 3 | WT 4 | |||||
---|---|---|---|---|---|---|---|---|

Time Stamp | Active Power [kW] | Wind Speed [m/s] | Active Power [kW] | Wind Speed [m/s] | Active Power [kW] | Wind Speed [m/s] | Active Power [kW] | Wind Speed [m/s] |

Max | 2059.5 | 22.3 | 2058.1 | 22.4 | 2059.9 | 21 | 2059.2 | 22.3 |

Min | 1632.2 | 10.1 | 1794.3 | 10.9 | 1372.1 | 11.2 | 1634.5 | 9.9 |

Time Stamp | Wind Speed WT1 [m/s] | Wind Speed WT2 [m/s] | Wind Speed WT3 [m/s] | Wind Speed WT4 [m/s] | LeqA [dBA] |
---|---|---|---|---|---|

01:20 | 15.6 | 16.1 | 16.5 | 16.2 | 40.6 |

01:30 | 14.9 | 15.8 | 15.4 | 15.3 | 38.5 |

01:40 | 13.6 | 14.0 | 14.2 | 14.5 | 36.9 |

01:50 | 11.7 | 12.4 | 12.5 | 12.2 | 38.1 |

02:00 | 10.7 | 11.3 | 11.5 | 12.0 | 38.2 |

02:10 | 10.1 | 10.9 | 11.2 | 9.9 | 38.4 |

02:20 | 11.7 | 11.0 | 11.9 | 10.9 | 38.7 |

02:30 | 11.6 | 12.4 | 12.9 | 10.7 | 41.1 |

02:40 | 13.5 | 14.9 | 14.6 | 14.7 | 41.7 |

02:50 | 16.6 | 18.6 | 17.8 | 17.0 | 45.5 |

03:00 | 18.9 | 18.7 | 19.5 | 19.6 | 49.7 |

03:10 | 21.3 | 21.3 | 20.5 | 21.6 | 47.3 |

03:20 | 22.3 | 22.4 | 21.0 | 22.3 | 47.6 |

RMSE | Person’s Correlation Coefficient |
---|---|

0.003788142 | 0.897 |

RMSE | Person’s Correlation Coefficient |
---|---|

0.0007370879 | 0.981 |

© 2019 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**

Iannace, G.; Ciaburro, G.; Trematerra, A. Wind Turbine Noise Prediction Using Random Forest Regression. *Machines* **2019**, *7*, 69.
https://doi.org/10.3390/machines7040069

**AMA Style**

Iannace G, Ciaburro G, Trematerra A. Wind Turbine Noise Prediction Using Random Forest Regression. *Machines*. 2019; 7(4):69.
https://doi.org/10.3390/machines7040069

**Chicago/Turabian Style**

Iannace, Gino, Giuseppe Ciaburro, and Amelia Trematerra. 2019. "Wind Turbine Noise Prediction Using Random Forest Regression" *Machines* 7, no. 4: 69.
https://doi.org/10.3390/machines7040069