DOI QR코드

DOI QR Code

Building of Prediction Model of Wind Power Generationusing Power Ramp Rate

Power Ramp Rate를 이용한 풍력 발전량 예측모델 구축

  • Hwang, Mi-Yeong (Dept. of Computer Science, Chungbuk National University) ;
  • Kim, Sung-Ho (Dept. of Computer Science, Chungbuk National University) ;
  • Yun, Un-Il (Dept. of Computer Science, Chungbuk National University) ;
  • Kim, Kwang-Deuk (Korea Institute of Energy Research) ;
  • Ryu, Keun-Ho (Dept. of Computer Science, Chungbuk National University)
  • Received : 2011.08.30
  • Accepted : 2011.09.13
  • Published : 2012.01.31

Abstract

Fossil fuel is used all over the world and it produces greenhouse gases due to fossil fuel use. Therefore, it cause global warming and is serious environmental pollution. In order to decrease the environmental pollution, we should use renewable energy which is clean energy. Among several renewable energy, wind energy is the most promising one. Wind power generation is does not produce environmental pollution and could not be exhausted. However, due to wind power generation has irregular power output, it is important to predict generated electrical energy accurately for smoothing wind energy supply. There, we consider use ramp characteristic to forecast accurate wind power output. The ramp increase and decrease rapidly wind power generation during in a short time. Therefore, it can cause problem of unbalanced power supply and demand and get damaged wind turbine. In this paper, we make prediction models using power ramp rate as well as wind speed and wind direction to increase prediction accuracy. Prediction model construction algorithm used multilayer neural network. We built four prediction models with PRR, wind speed, and wind direction and then evaluated performance of prediction models. The predicted values, which is prediction model with all of attribute, is nearly to the observed values. Therefore, if we use PRR attribute, we can increase prediction accuracy of wind power generation.

전 세계적으로 화석연료의 많이 사용이 증가되고 있으며 이로 인해 온실가스가 배출되어 지구 온난화와 환경오염이 심각해지고 있는 실정이다. 지구의 환경오염을 줄이기 위해서 무공해 청정에너지인 신재생에너지에 대한 관심이 증가되는 추세인데, 그중에서도 풍력발전은 환경오염 물질을 배출하지 않고, 자원량이 무한대이기 때문에 많은 관심을 받고 있다. 하지만, 풍력발전은 전력 생산량이 불규칙한 단점을 갖고 있어 풍력 터빈의 손상과 전력 생산량이 불규칙적인 문제를 야기하여 이러한 문제점을 보완하기 위해 풍력 발전량을 정확하게 예측하는 것이 중요하다. 풍력 발전량을 정확하게 예측하기 위해서 전력 생산량이 급증 또는 급감하는 것을 의미하는 ramp의 특성을 잘 활용해야 한다. 이 논문에서는 예측의 정확도를 높이기 위하여 다계층 신경망을 이용해 예측모델을 구축하였다. 구축된 예측모델은 흔히 사용되는 풍속, 풍향 속성뿐만 아니라 Power Ramp Rate(PRR) 속성까지 사용하였다. 구축된 풍력 발전량 예측모델은 앞서 말한 세 가지 속성을 모두 사용한 경우, 두 속성을 조합하여 사용한 경우 총 4가지 예측모델을 구축하였다. 구축된 4가지 예측모델을 성능평가 한 결과 PRR, 풍속, 풍향의 속성 모두를 사용한 예측모델의 예측 값이 풍력 터빈에서 관측된 관측 값에 가장 근접하였다. 그로 인해 PRR 속성을 사용하면 풍력 발전량의 예측 정확도를 향상 시킬 수 있었다.

Keywords

References

  1. Keungi Kim, "Prospects of Alternative Energy Development to Solve the Fossil Fuel Exhaustion and Global Warming", Hankuk University of Foreign Studies, graduation thesis, pp. 1-109, 2008.
  2. Yongcheol Gang, and Gyeongsu Guk, "Expansional plan of wind energy capacity of electric grid," KIEE, Vol. 59, No. 8, pp. 26-32, August 2010.
  3. KOREA INSTITUTE OF ENERGY RESEARCH (KIER), http://www.kier.re.kr/
  4. KOREA INSTITUTE OF ENERGY RESEARCH (KIER), http://210.98.3.184
  5. Seungguk Kim, "Analysis of New&Renewable Energy in the Korean Peninsula," Mokpo National Univ. graduation thesis, pp. 1-155, February 2007.
  6. C. Ferreira, J. Gama, L. Matias, A. Botterud and J. Wang, "A Survey on Wind Power Ramp Forecasting," Argonne National Laboratory(ANL), pp. 1-40, December 2010.
  7. R. Pyle, R. "Wind Ramp Prediction-Improved Predictability for Wind Energy Production," http://www.vaisala.com/en/press/vaisalanews/vaisalanews182/Pages/vn182_wind_ramp_prediction.aspx, January 2010.
  8. Haiyang Zheng and Andrew Kusiak, "Prediction of Wind Farm Power ramp rates: A Data-Mining Approach," JSEE, Vol. 131, August 2009.
  9. Pang-Ning Tan, Michael Steinbach, and Vipin Kumar, "INTORODUCTION TO DATA MINING," Pearson Education, Inc, pp. 246-256, 2006.
  10. Artificial Neural Network(ANN), http://blog.naver.com/oper_genius?Redirect=Log&logNo=20016457052
  11. Hyun-Goo Kim, Yung-Seop Lee, Moon-Seok Jang, "Cluster Analysis and Meteor-Statistical Model Test to Develop a Daily Forecasting Model for Jejudo Wind Power Generation," KENSS, Vol. 19, No. 10, pp. 129-1235, 2010.
  12. Hyun-Goo Kim, Yeong-Seup Lee, Mun-Seok Jang, Nam-Ho Kyong, "A Study on Development of a Forecasting Model of Wind Power Generation for Walryong Site," KSES, Vol. 26, No. 2, 2006.
  13. Sey-Yoon Kim and Sung-Ho Kim, "Comparative study on the performance of various wind speed predictors," KIISS, pp. 21-24, April 2011.
  14. Seong-Jun Kim and In-Yong Seo, "A Study on Statistical Forecasting of Wind Power Using Wavelet Decompositions," KIISS, pp. 151-154, April 2011.
  15. Keun-Suk Song, Hye-Suk Lee, "A Study on a Comparison of Error Magnitude Accuracies Among International Tourism Demand Forecasting Models," KTRA, pp. 83-111, July 2006.
  16. Lee, Choong-Ki and Song, Hak-Jun, "Selecting Most Appropriate Time Series Forecasting Model," KTRA, pp. 289-311, December 2007.
  17. Hyeongjin No, "Statistical analysis of multivariate analysis," Hyosan publishing company, pp. 628-629, 2007.
  18. Urban Engineering, "Time series analysis technique," pp.4-6.
  19. Park Yun-Ho, Kim Kyung-Bo, Her Soo-young, Lee Young-Mi, Huh Jong-Chul, "A Study on the Wind Data Analysis and Wind Speed Forecasting in Jeju Area," KSES, Vol. 30, No. 6, pp. 66-72, 2010.
  20. Young-Mi Lee, Myoung-Suk Yoo, Hong-Seok Choi, Yong-Jun kim, Young-Jun Seo, "A study on the Conceptual Design for the Real-time wind Power Prediction System in Jeju," KIEE, Vol. 59, No. 12, pp. 2202-2211, 2010.

Cited by

  1. A study on comparing short-term wind power prediction models in Gunsan wind farm vol.24, pp.3, 2013, https://doi.org/10.7465/jkdi.2013.24.3.585
  2. Design of short-term forecasting model of distributed generation power for wind power vol.12, pp.3, 2014, https://doi.org/10.14400/JDC.2014.12.3.211
  3. Access Control Protocol for Privacy Guarantee of Patient in Emergency Environment vol.12, pp.7, 2014, https://doi.org/10.14400/JDC.2014.12.7.279
  4. Privacy Protection Scheme of Healthcare Patients using Hierarchical Multiple Property vol.13, pp.1, 2015, https://doi.org/10.14400/JDC.2015.13.1.275
  5. 시계열 모형을 이용한 단기 풍력발전 예측 연구 vol.29, pp.7, 2016, https://doi.org/10.5351/kjas.2016.29.7.1373