Adaptive Wavelet Neural Network Based Wind Speed Forecasting Studies

다국어 초록 (Multilingual Abstract)

Wind has been a rapidly growing renewable power source for the last twenty years. Since wind behavior is chaotic in nature, its forecasting is not easy. At the same time, developing an accurate forecasting method is essential when wind farms are integrated into the power grid. In fact, wind speed forecasting tools can solve issues related to grid stability and reserve allocation. In this paper 30 hours ahead wind speed profile forecast is proposed using Adaptive Wavelet Neural Network (AWNN). The implemented AWNN uses a Mexican hat mother Wavelet, and Morlet Mother Wavelet for seven, eight and nine levels decompositions. For wind speed forecasting, the time series data on wind speed has been gathered from the National Renewable Energy Laboratory (NREL) website. In this work, hourly averaged 10-min wind speed data sets for the year 2004 in the Midwest ISO region (site number 7263) is taken for analysis. Data sets are normalized in the range of [-1, 1] to improve the training performance of forecasting models. Total 8760 samples were taken for this forecasting analysis. After the forecasting phase, statistical parameters are calculated to evaluate system accuracy, comparing different configurations.

목차 (Table of Contents)

• Abstract
• 1. Introduction
• 2. Wavelets
• 3. Results and Discussions
• 4. Conclusions
• References

참고문헌 (Reference)

1 "http://www.nrel.gov/wind/integrationdatase ts/eastern/data.html"

2 Mudathir Funsho Akorede, "Wavelet Transforms: Practical Applications in Power Systems" 대한전기학회 4 (4): 168-174, 2009

3 Eduardo Martin Moraud, "Wavelet Networks" 2009

4 Potter C. W., "Very short-term wind forecasting for Tasmanianpower generation" 21 (21): 965-972, 2006

5 Han Shuang, "Taboo Search Algorithm Based ANN Model for Wind Speed Prediction" 2007

6 Andrew Kusiak, "Short-Term Prediction of Wind Farm Power: A Data Mining Approach" 24 (24): 125-136, 2009

7 Khan, A.A., "One day ahead wind speed forecasting using wavelets" 1-5, 2009

8 "National Renewable Energy Laboratory"

9 T. Barbounis, "Longterm wind speed and power forecasting using local recurrent neural network models" 21 (21): 273-284, 2006

10 Ramesh Babu. N, "Improving Forecast Accuracy of Wind Speed Using Wavelet Transform and Neural Networks" 대한전기학회 8 (8): 559-564, 2013

11 Catalao J. P. S., "Hybrid wavelet-PSO-ANFIS approach for shorttermwind power forecasting in Portugal" 2 (2): 50-59, 2011

12 Guoqiang Zhang, "Forecasting With artificial neural networks: The state of the art" 14 : 35-62, 1998

13 Gomes, P., "Comparison of statistical wind speed forecastingmodels" 56-61, 2011

14 George Sideratos, "An Advanced Statistical Method for Wind Power Forecasting" 22 (22): 258-265, 2007

15 Pindoriya. N. M, "An Adaptive Wavelet Neural Network-Based Energy Price Forecasting in Electricity Markets" 23 (23): 1423-1432, 2008

16 Bhaskar. K., "AWNN-Assisted Wind Power Forecasting Using Feed-Forward Neural Network" 3 (3): 306-315, 2012

17 Liang Wu, "A study on wind speed prediction using artificialneural network at Jeju Island in Korea" 1-4, 2009

18 D. Rakesh Chandra, "A detailed literature review on wind forecasting" 630-634, 2013

19 Xing-Jie Liu, "A Novel Approach for Wind Speed Forecasting Basedon EMD and Time-Series Analysis" 1-4, 2009

20 Song Jia, "A New Method for The Short-term Wind Speed Forecasting" 1320-1324, 2011