Kusiak.qxd_Outsourcing_book_temp.qxd 26/02/2010 10:17 Page 68
Short-term Prediction of Windfarm Power – A Data-driven Approach
A 10-second data set was randomly selected from the same windfarm scales. The virtual turbine is successfully simulated by SCADA data
and used to test the virtual models. The results indicate that the power collected from multiple wind turbines using selected parameters. This
output and rotor speed are accurately predicted. Note that the test implies that the virtual models can be used to predict the power output
data represent different measurements taken at different turbines. The and rotor speed for a turbine of interest using the data collected at
high prediction accuracy of the power output and rotor speed is other turbines.
reinforced in Figure 4.
There are still other interesting research questions that need to be
Conclusion answered. For example, in a temporal data-mining scenario, an
Wind energy is believed to be one of the most promising renewable identified process model should be updated periodically. Future
energies on Earth. The wind energy industry is expanding rapidly, not research can focus on how to extend a model’s prediction accuracy
only in the US but also in Europe and Asia. However, wind energy is over a long time horizon.
facing various challenges, which demands innovative research to
secure its future in the power and energy market. Any power optimisation strategy should consider active power and torque
and add more constraints from mechanical and electrical domains. A
Predictive engineering is particularly important for transforming a multi-objective optimisation model allowing for a comprehensive
windfarm into a real wind power plant. In this article, windfarm power optimisation of wind turbines is necessary in future studies. n
prediction models were developed from different data sources. Time
series windfarm power prediction models for different prediction Acknowledgements
horizons were built by data-mining algorithms. The time series The sponsorship of the Iowa Energy Center (Grant IEC 07-01) and the
prediction models accurately predict windfarm power on different time contribution of Haiyang Zheng are acknowledged.
1. Piramuthu S, Evaluating feature selection methods for based on cluster center fuzzy logic modeling, J Wind Eng Ind simulate and forecast wind speed and wind power, J Appl
learning in data mining applications, Proceedings of the Thirty- Aerod, 2008;96(5):611–20. Meteorol, 1984;23:1184–95.
First Hawaii International Conference on System Science, Kohala 4. Datta R, Ranganathan VT, A method of tracking the 6. Kusiak A, Zheng HY, Song Z, Short-term prediction of wind
Coast, HI, 1998;5,:294–302. peak power points for a variable speed wind energy farm power: a data mining approach, IEEE Trans Energ Convers,
2. Tan PN, Steinbach M, Kumar V, Introduction to Data Mining, conversion system, IEEE Trans Energ Convers, 2003;1(1): 2009;24(1):125–36.
Addison Wesley, 2006. 163–8. 7. Kusiak A, Li W, Virtual models for prediction of wind turbine
3. Taner U, Ahmet A, Wind turbine power curve estimation 5. Brown BG, Katz RW, Murphy AH, Time series models to parameters, IEEE Trans Energ Convers, 2010, in print.
As leading experts in gear- & gearbox technology, Hansen
Transmissions manufactures wind turbine gearboxes with the
highest precision. Our unique designs deliver the highest torque
capacity in the market. We ensure that our gears achieve the
lowest noise and vibration levels, whilst delivering the highest
reliability and quality.
As the biggest independent gearbox specialist, with more than
85 years of in-house manufacturing experience, we design and
produce innovative gearboxes and drive trains. Our process
knowledge and control are second to none and the use of
advanced measuring techniques enables us to accurately verify
and optimize our gears.
In an industry with a strong focus on the reduction of the kWh
cost of renewable energy, we ensure that we meet our customers’
needs to where microns matter.
Hansen Transmissions International nv
Microns matter
De Villermontstraat 9
2550 Kontich, Belgium
T + 32 3 450 58 00
F + 32 3 450 58 10
.hansentransmissions.com
www
info.wind@hansentransmissions.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108