한국통신학회논문지 (The Journal of Korean Institute of Communications and Information Sciences)

  • 제42권5호
  • /
  • Pages.1085-1092
  • /
  • 2017
  • /
  • 1226-4717(pISSN)
  • /
  • 2287-3880(eISSN)
한국통신학회 (The Korean Institute of Commucations and Information Sciences)
권호 표지
DOI QR코드

DOI QR Code

풍향과 풍속의 특징을 이용한 SVR기반 단기풍력발전량 예측

Forecasting of Short-term Wind Power Generation Based on SVR Using Characteristics of Wind Direction and Wind Speed

  • Kim, Yeong-ju (Mokpo National University Department of Computer Engineering) ;
  • Jeong, Min-a (Mokpo National University Department of Computer Engineering) ;
  • Son, Nam-rye (Honam University Department of Information and Communication Engineering)
  • 투고 : 2017.01.31
  • 심사 : 2017.04.25
  • 발행 : 2017.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문은 풍력발전예측의 정확도 개선을 위하여 바람의 특성을 반영한 풍력발전량예측 방법을 제안한다. 제안한 방법은 크게 바람의 특성을 추출하는 부분과 발전량을 예측하는 부분으로 구성된다. 바람의 특성을 추출하는 부분은 발전량, 풍향과 풍속의 상관분석을 이용한다. 풍향과 풍속의 상관관계를 근거로 K-means 방법으로 클러스터링하여 특징 벡터를 추출한다. 예측하는 부분은 임의의 실수값을 예측 할 수 있도록 SVM을 일반화 한 SVR을 이용하여 기계학습을 한다. 기계학습은 바람의 특성을 반영한 제안한 방법과 바람의 특성을 반영하지 않은 기존방법을 비교 실험하였다. 또한, 제안한 방법의 정확도와 타당성을 검증하기 위하여 장소가 상이한 제주도 풍력발전단지 3지역에서 수집된 데이터를 사용하였다. 실험결과, 제안한 방법의 오차가 일반적인 풍력발전예측 오차보다 개선되었다.

In this paper, we propose a wind forecasting method that reflects wind characteristics to improve the accuracy of wind power prediction. The proposed method consists of extracting wind characteristics and predicting power generation. The part that extracts the characteristics of the wind uses correlation analysis of power generation amount, wind direction and wind speed. Based on the correlation between the wind direction and the wind speed, the feature vector is extracted by clustering using the K-means method. In the prediction part, machine learning is performed using the SVR that generalizes the SVM so that an arbitrary real value can be predicted. Machine learning was compared with the proposed method which reflects the characteristics of wind and the conventional method which does not reflect wind characteristics. To verify the accuracy and feasibility of the proposed method, we used the data collected from three different locations of Jeju Island wind farm. Experimental results show that the error of the proposed method is better than that of general wind power generation.

키워드

참고문헌

  1. A. S. Kim, H. S, Han, K. Y. Bae, and D. K. Sung, "Wind power forecasting based support vector machine for a large-scale wind farm in jeju island," in Proc. KICS Int. Conf. Commun., pp. 11-12, Kangwon, Korea, Jan. 2016.
  2. A. M. Foley, P. G. Leahy, and E. J. McKeogh, "Wind power forecasting & prediction method," IEEE, 9th Int. Conf. Environ. and Electrical Eng., pp. 16-19, May 2010.
  3. I. Y. Seo, B. N. Ha, S. O. Kim, W. N. Koong, D. W. Seo, and S. J. Kim, "Short term wind power prediction using wavelet transform and ARIMA," J. Energy and Power Eng., pp. 1786-1790, Jun. 2012.
  4. K. Parks and Y. H. Wan, Wind energy forecasting : A collaboration of the national center for atmospheric research(NCAR) and xcel energy, NREL/SR-5500-52233, Oct. 2011.
  5. Y. Y. Hong, T. H. Yu, and C. Y. Liu, "Hour-Ahead wind speed and power forecasting using empirical mode decomposition," Energies, vol. 6, no. 12, pp. 6137-6152, Jun. 2013. https://doi.org/10.3390/en6126137
  6. G. Sideratos and N. Hatziargyriou, "An advanced statistical method for wind power forecasting," IEEE Trans. Power Syst., vol. 22, no. 1, pp. 258-265, Feb. 2007. https://doi.org/10.1109/TPWRS.2006.889078
  7. M. Negnevitsky and C. Potter, "Innovative short-term wind generation prediction techniques," IEEE Power Syst. Conf. and Exposition, pp. 60-65, 2006.
  8. T. El-Fouly, E. El-Saadany, and M Salama, "Grey predictor for wind energy conversion systems output power prediction," IEEE Trans. Power Syst., vol. 21, no. 3, pp. 1450-1452. Aug. 2006. https://doi.org/10.1109/TPWRS.2006.879246
  9. J. Palomares-Salas, J. Rosa, J. Ramiro, J. Melgar, A. aguera, and A. Moreno, "ARIMA vs. Neural networks for wind speed forecasting," CIMSA 2009 - Int. Conf. Computational Intell. for Measurement Syst. and Appl., pp. 129-133, 2009.
  10. I. Damousis, M. Alexiadis, J. Theocharis, and P. Dokopoulos, "A fuzzy model for wind speed prediction and power generation in wind parks using spatial correlation," IEEE Trans. Energy Conversion, vol. 19, no. 2, pp. 352-361, Jul. 2008.
  11. M. G. Choi, H. G, Lee, and S. C. Lee, "Evil-twin detection scheme using SVM with multi-factors," J. KICS, vol. 40, no. 2, pp. 334-348, Feb. 2015. https://doi.org/10.7840/kics.2015.40.2.334
  12. K. Kim, Y. Park, J. Park, K. Ko, and J. Huh, "Feasibility study on wind power forecasting using MOS forecasting result of KMA," JKSES, vol. 30, no. 2, Feb. 2010.
  13. Y. Ho. Park, K. B. Kim, S. Y. Her, Y. M. Lee, and J. C. Huh, "A study on the wind data analysis and wind speed forecasting in Jeju area," J. Korean Solar Energy Soc., vol. 30, no. 6, 2010.
  14. D. H. Shin, K. K. An, S. C. Choi, and H. K. Choi, "Malicious traffic detection using K-means," J. KICS, vol. 41, no. 2, pp. 277-284, Feb. 2016. https://doi.org/10.7840/kics.2016.41.2.277
  15. Y. I. Kim, H. Y. Jo, and Y. J. Park, "A method of nu-SVR learning with a set of basis functions," KIIS, vol. 13, no. 3, pp. 316-321, Jun. 2003.
  16. J. Han and M. Kamber, Data Mining Concepts and Techniques, p. 172, 2006.
  17. C. G. Park, "Prediction of software development cost using support vector regression," The Korean Operations Res. and Management Sci. Soc., vol. 23, no. 2, pp. 75-91, Nov. 2006.
  18. R. J. Hyndman and A. B. Koehler, "Another look at measures of forecast accuracy," Int. J. Forecasting, vol. 22, no. 4, pp. 679-688, 2006. https://doi.org/10.1016/j.ijforecast.2006.03.001

피인용 문헌

  1. K-평균 군집화 알고리즘 및 딥러닝 기반 군중 집계를 이용한 전염병 확진자 접촉 가능성 여부 판단 모니터링 시스템 제안 vol.9, pp.3, 2017, https://doi.org/10.30693/smj.2020.9.3.122