KIISE Transactions on Computing Practices (정보과학회 컴퓨팅의 실제 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

A Dynamic Piecewise Prediction Model of Solar Insolation for Efficient Photovoltaic Systems

효율적인 태양광 발전량 예측을 위한 Dynamic Piecewise 일사량 예측 모델

  • 양동헌 (과학기술연합대학원대학교 컴퓨터소프트웨어전공) ;
  • 여나영 (과학기술연합대학원대학교 컴퓨터소프트웨어전공) ;
  • 마평수 (과학기술연합대학원대학교 컴퓨터소프트웨어전공)
  • Received : 2017.08.04
  • Accepted : 2017.10.20
  • Published : 2017.11.15
⟨ Previous Next ⟩

Abstract

Although solar insolation is the weather factor with the greatest influence on power generation in photovoltaic systems, the Meterological Agency does not provide solar insolation data for future dates. Therefore, it is essential to research prediction methods for solar insolation to efficiently manage photovoltaic systems. In this study, we propose a Dynamic Piecewise Prediction Model that can be used to predict solar insolation values for future dates based on information from the weather forecast. To improve the predictive accuracy, we dynamically divide the entire data set based on the sun altitude and cloudiness at the time of prediction. The Dynamic Piecewise Prediction Model is developed by applying a polynomial linear regression algorithm on the divided data set. To verify the performance of our proposed model, we compared our model to previous approaches. The result of the comparison shows that the proposed model is superior to previous approaches in that it produces a lower prediction error.

일사량은 태양광 발전시스템의 전력 생산량에 가장 큰 영향을 미치는 기상요소이며, 다른 기상요소들과 달리 기상청의 일기예보를 통해 제공받을 수 없다. 따라서 효율적인 태양광 발전시스템 운용을 위해 일사량 예측에 관한 연구는 필수적이다. 본 연구는 기상정보 데이터 기반의 Dynamic Piecewise 일사량 예측 모델을 제안한다. Dynamic Piecewise 일사량 예측 모델은 유사한 태양고도와 유사한 날씨의 데이터 조각들로 나누어 학습하기 위해, 예측하는 시점의 태양고도와 운량을 기준으로 전체 데이터를 동적으로 나눈 후 기계학습 알고리즘인 다중 선형회귀 알고리즘으로 학습하여 일사량을 예측하는데 사용된다. 본 연구의 성능을 검증하기 위해 제안 모델인 Dynamic Piecewise 일사량 예측 모델과 이전 연구에서 제안한 모델, 기존의 상관관계식 기반 일사량 예측 모델에 동일한 기상정보 데이터 셋을 적용하여 비교하였으며, 비교결과 본 연구에서 제안한 모델이 가장 정확한 일사량 예측 성능을 보였다.

Keywords

Acknowledgement

Grant : 경량 임베디드 디바이스용 저전력 OS 지원 통합개발 솔루션 개발, 빅데이터 기반 태양광 발전 시스템 결함 및 사용자 전력소비 예측 기술 개발

Supported by : 정보통신기술진흥센터, UST

References

  1. LG Economic Research Institute, Bigbang Future : 2030 LG Economic Research Institute Future Report, The Korea Economic Daily, 2016. (in Korean)
  2. Jong-Min Won, Geun-Young Doe, Su-Yun Jung, Jung-Jae Lee, "Predict Solar Radiation for Photovoltaic of Maritime City," Proc. of the KINPR Spring Conference, pp. 197-198, 2010. (in Korean)
  3. Jong-Min Won, Geun-Young Doe, Na-Ri Heo, "Predict Solar Radiation According to Weather Report," Journal of KINPR, Vol. 35, No. 5 pp. 387-392, Jun. 2011. (in Korean)
  4. Sin-Young Do, "The Estimate of Hourly Solar Radiation of Small and Medium Cities for Building Energy Simulation," M.S., Hoseo University, 2016. (in Korean)
  5. D.K. Jo, I.S. Chun, M.S. Jeon, Y.H. Kang, C.M. Auh, "Atmospheric Clearness Analysis of Major Cities in Korea Using Solar Radiation," Journal of the KSES, Vol. 21, No. 2, pp. 19-25, Jan. 2001. (in Korean)
  6. Zhang Qingyuan, Joe Huang, Lang Siwei, "Development of Typical Year Weather Data for Chinese Locations," ASHRAE Transactions, Vol. 108, pp. 1063-1075, Jun. 2002.
  7. Amit Kumar Yadav, S.S. Chandel, "Solar radiation prediction using Artificial Neural Network techniques: A review," Renewable and Sustainable Energy Reviews(RSER), Vol. 33, pp. 772-781, May. 2014. https://doi.org/10.1016/j.rser.2013.08.055
  8. Kuk Yeol Bae, Han Seung Jang, Dan Keun Sung, "Hourly Solar Irradiance Prediction Based on Support Vector Machine and Its Error Analysis," IEEE Transactions on Power Systems, Vol. 32, No. 2, pp. 935-945, Mar. 2017. https://doi.org/10.1109/TPWRS.2016.2569608
  9. Dong Hun Yang, Na Young Yeo, Sang Cheol Kim, Jeong-Woo Lee, Seon-Tae Kim, Pyeongsoo Mah, "A Piecewise Prediction Model of Solar Radiation using Weather Sensing Information for stand-alone Photovoltaic Systems," Proc of KIISE : KCC2017, pp. 15-17, 2017. (in Korean)
  10. Tae-Ho Kim, Seong-Yeon Yoo, Kyu-Hyun Han, Hyounh-Chul Kang, Hong-Ki Yoon, "A Study on Solar Radiation Model for Prediction of Solar Insolation," Proc of KSME Spring and Fall Conference, pp. 670-675, 2013. (in Korean)
  11. A. Angstrom, "Solar and Terrestrial radiation, Report to the international commission for solar research on actinometric investigations of solar and atmospheric radiation," Quarterly Journal of The Royal Meteorological Society, Vol. 50, No. 210, pp. 121-126, Apr. 1924. https://doi.org/10.1002/qj.49705021008
  12. Ahram Song, Wonseok Choi, Changyeol Yun, Yongil Kim, "Evaluation of Clear Sky Models to Estimate Solar Radiation over the Korean Peninsula," Journal of the KSGPC, Vol. 33, No. 5, pp. 415-426, Oct. 2015. (in Korean)
  13. J. Grief, K. Scharmer, ERSA : European Solar Radiation Atlas. 4th Ed., Presses de Ecole, Paris, France, 1999.
  14. Benjamin Y.H. Liu, Richard C. Jordan, "The interrelationship and characteristic distribution of direct, diffuse and total solar radiation," Solar Energy, Vol. 4, No. 3, pp. 1-19, Jul. 1960. https://doi.org/10.1016/0038-092X(60)90062-1
  15. Dok-Ki Jo, Eun-Ill Kim, Tae-Kyu Lee, Il-Soo Chun, Hong-Seok Jeon, Chung-Moo Auh, "A Study on the Estimating Solar Radiation by Empirical Regression Models," Journal of the KSES, Vol. 14, No. 2, pp. 17-28, 1994. (in Korean)
  16. J. H. Yoon, "Performance Validation of Five Direct/Diffuse Decomposition Models Using Measured Direct Normal Insolation of Seoul," Journal of the KSES, Vol. 20, No. 1, pp. 45-54, Mar. 2000. (in Korean)
  17. Ji-Soo Shim, Doo-Sam Song, "Applicability of the Solar Irradiation Model in Preparation of Typical Weather Data Considering Domestic Climate Conditions," Journal of SAREK, Vol. 28, No. 12, pp. 467-476, Dec. 2016. (in Korean)
  18. Shinwoo Hyun, Kwang Soo Kim, "Assessment of the Angstrom-Prescott Coefficients for Estimation of Solar Radiation in Korea," Journal of KSAFM, Vol. 18, No. 4, pp. 221-232, 2016. (in Korean)
  19. Korea Open Weather Data Portal, "data.kma.go.kr"