DOI QR코드

DOI QR Code

Analysis of prediction model for solar power generation

태양광 발전을 위한 발전량 예측 모델 분석

  • 송재주 (한전 전력연구원) ;
  • 정윤수 (목원대학교 정보통신공학과) ;
  • 이상호 (충북대학교 전자정보대학 소프트웨어학과)
  • Received : 2014.01.08
  • Accepted : 2014.03.20
  • Published : 2014.03.28

Abstract

Recently, solar energy is expanding to combination of computing in real time by tracking the position of the sun to estimate the angle of inclination and make up freshly correcting a part of the solar radiation. Solar power is need that reliably linked technology to power generation system renewable energy in order to efficient power production that is difficult to output predict based on the position of the sun rise. In this paper, we analysis of prediction model for solar power generation to estimate the predictive value of solar power generation in the development of real-time weather data. Photovoltaic power generation input the correction factor such as temperature, module characteristics by the solar generator module and the location of the local angle of inclination to analyze the predictive power generation algorithm for the prediction calculation to predict the final generation. In addition, the proposed model in real-time national weather service forecast for medium-term and real-time observations used as input data to perform the short-term prediction models.

최근 태양광에너지는 실시간 태양의 위치를 추적하여 모듈경사각과 이루는 갓을 산정하여 일사량을 보정하는 부분에서 컴퓨팅과의 결합이 확대되고 있다. 태양광 발전은 태양의 위치에 따라 출력변동이 심하고 출력 예측이 어려워 효율적인 전력 생산을 위해서 신재생에너지를 전력계통에 안정적으로 연계할 수 있는 기술이 필요하다. 본 논문에서는 실증단지 내 발전단지의 실시간 기상자료 예측값을 이용하여 최종적으로 태양광 발전량 예측값을 산정하는 태양광 발전을 위한 발전량 예측 모델을 분석한다. 태양광 발전량은 태양광 발전기별 모듈특성, 온도 등을 감안하여 보정계수를 입력하고 예측 지역의 위치 경사각을 분석하여 발전량 예측 계산 알고리즘을 통해 최종 발전량을 예측한다. 또한, 제안 모델에서는 실시간 기상청 관측자료와 실시간 중기 예측 자료를 입력 자료로 사용하여 단기 예측 모델을 수행한다.

Keywords

References

  1. B. Abraham and J. Ledolter(2005), "Statistical methods for forecasting", Wiley, New York.
  2. G. E. P. Box, G. M. Jenkins and , G. C. Reinsel(1994), "Time series analysis, forecasting and control", 3rd Ed., Prentice Hall, Englewood Cliffs, New Jersey.
  3. Z. Guo, W. Zhao, H. Lu and J. Wang(2012), "Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model", Renewable Energy, vol. 37, pp. 241-249. https://doi.org/10.1016/j.renene.2011.06.023
  4. S. Y. Kim and S. H. Kim(2011), "Study on the predication of wind power generation based on artificial neural netowrk", Journal of Institute of Control, Robotics and System, vol. 17, pp. 1173-1178. https://doi.org/10.5302/J.ICROS.2011.17.11.1173
  5. H. Lee(2012), "Analysis of time series models for consumer price index", Journal of the Korean Data & Information Science Society, vol. 23, pp. 535-542. https://doi.org/10.7465/jkdi.2012.23.3.535
  6. A. More and M. C. Deo(2003), "Forecasting wind with neural networks", marine Structure, vol. 16, pp. 35-49. https://doi.org/10.1016/S0951-8339(02)00053-9
  7. K. J. Oh, T. Y. Kim, K. Jung and C. Kim(2011), "Stock market stability index via linear and neural network autoregressive model", Journal of the Korean Data & Information Science Society, vol. 22, pp. 335-351.
  8. W. J. e. Potts(2000), "Neural network modeling course notes", SAS Institute Inc., Cary, NC.
  9. J. powers and M. M. Ali(2000), "Application of neural networks in aluminum corrosion", Journal of the Korean Data & Information Science Society, vol. 1, pp. 157-172.
  10. A. Sfetsos(2002), "A novel approach for the forecasting of mean hourly wind speed time series", Renewable Energy, vol. 27, pp. 163-174. https://doi.org/10.1016/S0960-1481(01)00193-8
  11. Y. S. Lee, J. Kim, M. S. Jang and H. G. Kim(2013), "A study on comparing short-term wind power predication models in Gunsan wind farm", Journal of the Korean Data & Information Science Society, vol. 24, no. 3, pp. 585-592 https://doi.org/10.7465/jkdi.2013.24.3.585