A novel method to optimize electricity generation from wind energy

Abstract We present and discuss a new technique based on information theory to detect in advance favorable periods of wind activity (positive ramps) for electricity generation. In addition this technique could also help in the analysis of plant operation and management protocols design. Real data from wind power plants in Germany is used; this information is freely available in the internet with reliable registers every 15 min. A simple protocol to mix such wind energy production with electricity coming from conventional sources is proposed as a way to test the proposed algorithm. The eight-year period 2010–2017 is analyzed looking for different behaviors in wind activity. The first five years (2010–2014) are employed to calibrate the method, while the remaining three years (2015–2017) are used to test previous calibration without any further variation in the tuning possibilities described below. Thus, the proposed protocol is tried on under different seasonal wind conditions. Both the algorithm and the general protocol could be adjusted to optimize performances according to regional conditions. In addition, this algorithm can also be used in retrospective studies to adjust productivity to operational conditions.

[1]  Sarah M. Ryan,et al.  Day-ahead hourly electricity load modeling by functional regression , 2016 .

[2]  J. Farradane,et al.  Information Science , 1971, Nature.

[3]  I. González-Aparicio,et al.  Impact of wind power uncertainty forecasting on the market integration of wind energy in Spain , 2015 .

[4]  Hui Liu,et al.  Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction , 2012 .

[5]  Cristobal Gallego-Castillo,et al.  A review on the recent history of wind power ramp forecasting , 2015 .

[6]  Eugenio E. Vogel,et al.  Information theory applied to econophysics: stock market behaviors , 2014 .

[7]  Ergin Erdem,et al.  ARMA based approaches for forecasting the tuple of wind speed and direction , 2011 .

[8]  Akin Tascikaraoglu,et al.  A review of combined approaches for prediction of short-term wind speed and power , 2014 .

[9]  E. Vogel,et al.  Information theory as a tool to improve individual pensions: The Chilean case , 2015 .

[10]  Ponnuthurai Nagaratnam Suganthan,et al.  Ensemble methods for wind and solar power forecasting—A state-of-the-art review , 2015 .

[11]  Juan G. Roederer.  Information and its role in nature , 2005 .

[13]  Maria Grazia De Giorgi,et al.  Assessment of the benefits of numerical weather predictions in wind power forecasting based on stati , 2011 .

[14]  E. Vogel,et al.  Derivation of a measure of systolic blood pressure mutability: a novel information theory-based metric from ambulatory blood pressure tests. , 2016, Journal of the American Society of Hypertension : JASH.

[15]  Jianzhou Wang,et al.  A combined model based on data pre-analysis and weight coefficients optimization for electrical load forecasting , 2015 .

[16]  E. Vogel,et al.  Time-series analysis of earthquake sequences by means of information recognizer , 2017 .

[17]  Song Li,et al.  An ensemble approach for short-term load forecasting by extreme learning machine , 2016 .

[18]  E. Vogel,et al.  Phase diagram and reentrance for the 3D Edwards-Anderson model using information theory , 2014 .

[19]  Yang Fu,et al.  Short-term wind power forecasts by a synthetical similar time series data mining method , 2018 .

[20]  Aoife Foley,et al.  Current methods and advances in forecasting of wind power generation , 2012 .

[21]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[22]  E. Vogel,et al.  Data compressor designed to improve recognition of magnetic phases , 2012 .

[23]  Seref Sagiroglu,et al.  Data mining and wind power prediction: A literature review , 2012 .

[24]  Daniel Ambach,et al.  Short-term wind speed forecasting in Germany , 2015, 1509.03116.