Data Confidence Applied to Wind Turbine Power Curves

  • Roberto Milton Scheffel UTFPR
  • José Luís Hoffmann UFSC
  • Leonardo Horstmann UFSC
  • Gustavo de Araujo UFSC
  • Antônio Fröhlich UFSC
  • Tiago Matsuo AQTech
  • Vitor Pohlenz AQTech
  • Marcos Nishioka AQTech

Resumo


This paper addresses the problem of reducing Wind Turbines Power Curve modeling error and false-positive classifications of incoming wind speed and respective power generation data with a real-time approach based on a confidence assignment algorithm. The approach builds upon an IoT Platform with support to the execution of domain-specific workflows to process incoming data, removing outliers and executing an algorithm that operates based on the difference between the data read by the sensors and the values predicted by an Artificial Neural Network (ANN). These values are used to calculate a confidence level, that can be used to identify a defective sensor, as well as to ignore wrong values that can lead to wrong diagnostics. The processed data is either used to build a model or is compared to an existing model to check its validity. The proposed approach achieved an average increase of 2.96% on the model coverage and 14.96% average reduction on the false-positive rates.

Palavras-chave: Wind Turbines, Internet of Things, Confidence Attribution, Machine Learning, Real-Time data

Referências

S. Shokrzadeh M. J. Jozani and E. Bibeau "Wind turbine power curve modeling using advanced parametric and nonparametric methods" IEEE Trans. on Sustainable Energy vol. 5 no. 4 pp. 1262-1269 Oct. 2014.

M. Lydia S. S. Kumar A. I. Selvakumar and G. E. P. Kumar "A comprehensive review on wind turbine power curve modeling techniques" Renewable and Sustainable Energy Reviews vol. 30 pp. 452-460 Feb. 2014.

M. S. M. Raj M. Alexander and M. Lydia "Modeling of wind turbine power curve" ISGT2011-India Dec. 2011.

N. Bokde A. Feijoo and D. Villanueva "Wind turbine power curves based on the weibull cumulative distribution function" Applied Sciences vol. 8 no. 10 pp. 1757 Sep. 2018.

L. A. Osadciw Y. Yan X. Ye G. Benson and E. White Wind Turbine Diagnostics Based on Power Curve Using Particle Swarm Optimization Berlin Heidelberg:Springer Berlin Heidelberg pp. 151-165 2010.

Y. Zhao L. Ye W. Wang H. Sun Y. Ju and Y. Tang "Data-driven correction approach to refine power curve of wind farm under wind curtailment" IEEE Trans. on Sustainable Energy vol. 9 no. 1 pp. 95-105 Jan. 2018.

F. Castano S. Strzelczak A. Villalonga R. E. Haber and J. Kos-sakowska "Sensor reliability in cyber-physical systems using internet-of-things data: A review and case study" Remote sensing vol. 11 no. 19 pp. 2252 2019.

R. K. Pandit and D. Infield "Using gaussian process theory for wind turbine power curve analysis with emphasis on the confidence intervals" 2017 6th International Conference on Clean Electrical Power (ICCEP). Jun. 2017.

X. Ye Z. Lu Y. Qiao Y. Min and M. O'Malley "Identification and correction of outliers in wind farm time series power data" IEEE Trans. on Power Systems vol. 31 no. 6 pp. 4197-4205 Nov. 2016.

N. Song X. Hu and N. Li "Anomaly detection of wind turbine generator based on temporal information" Proceedings of the 2019 7th International Conference on Information Technology: IoT and Smart City. Dec. 2019.

Y. Hu Y. Qiao J. Liu and H. Zhu "Adaptive confidence boundary modeling of wind turbine power curve using SCADA data and its application" IEEE Trans. on Sustainable Energy vol. 10 no. 3 pp. 1330-1341 Jul. 2019.

M. Poggi G. Agresti F. Tosi P. Zanuttigh and S. Mattoccia "Confi-dence estimation for ToF and stereo sensors and its application to depth data fusion" IEEE Sensors Journal vol. 20 no. 3 pp. 1411-1421 Feb. 2020.

D. Villanueva and A. Feijoo "A review on wind turbine deterministic power curve models" Applied Sciences vol. 10 no. 12 Jun. 2020.

A. A. Frohlich "SmartData: an IoT-ready API for sensor networks" International Journal of Sensor Networks vol. 28 no. 3 pp. 202 2018.

Z. Noshad N. Javaid T. Saba Z. Wadud M. Q. Saleem M. E. Alzahrani et al. "Fault detection in wireless sensor networks through the random forest classifier" Sensors vol. 19 no. 7 pp. 1568 2019.

T. Muhammed and R. A. Shaikh "An analysis of fault detection strategies in wireless sensor networks" Journal of Network and Computer Applications vol. 78 pp. 267-287 2017.

R. M. Scheffel and A. A. Frhlich "WSN data confidence attribution using predictors" 2018 Eighth Latin-American Symposium on Dependable Computing (LADC). Oct. 2018.

R. M. Scheffel and A. A. Frohlich "Increasing sensor reliability through confidence attribution" Journal of the Brazilian Computer Society vol. 25 no. 1 pp. 1-20 2019.

W. Dixon "Processing data for outliers" Biometrics vol. 9 no. 1 pp. 74-89 1953.

J. W. Osborne and A. Overbay "The power of outliers (and why researchers should always check for them)" Practical Assessment Research and Evaluation vol. 9 no. 1 pp. 6 2004.

"Danish Wind Industry Association" The power curve of a wind turbine. 2020 [online] Available: http://dromsterre.dk/wp-content/wind/miller/windpower%20web/en/tour/wres/pwr.htm.

B. C. Ross "Mutual information between discrete and continuous data sets" PloS one vol. 9 no. 2 2014.

A. B. Sharma L. Golubchik and R. Govindan "Sensor faults: Detection methods and prevalence in real-world datasets" ACM Trans. on Sensor Networks (TOSN) vol. 6 no. 3 2010.
Publicado
23/11/2020
SCHEFFEL, Roberto Milton; HOFFMANN, José Luís; HORSTMANN, Leonardo; DE ARAUJO, Gustavo; FRÖHLICH, Antônio; MATSUO, Tiago; POHLENZ, Vitor; NISHIOKA, Marcos. Data Confidence Applied to Wind Turbine Power Curves. In: SIMPÓSIO BRASILEIRO DE ENGENHARIA DE SISTEMAS COMPUTACIONAIS (SBESC), 10. , 2020, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 41-48. ISSN 2237-5430.