The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

A study on solar energy forecasting based on time series models

시계열 모형과 기상변수를 활용한 태양광 발전량 예측 연구

  • Lee, Keunho (Department of Applied Statistics, Chung-Ang University) ;
  • Son, Heung-gu (Department of Aviation, The Korea Transport Institute) ;
  • Kim, Sahm (Department of Applied Statistics, Chung-Ang University)
  • 이근호 (중앙대학교 응용통계학과) ;
  • 손흥구 (한국교통연구원 항공교통본부) ;
  • 김삼용 (중앙대학교 응용통계학과)
  • Received : 2017.11.27
  • Accepted : 2017.12.11
  • Published : 2018.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

This paper investigates solar power forecasting based on several time series models. First, we consider weather variables that influence forecasting procedures as well as compare forecasting accuracies between time series models such as ARIMAX, Holt-Winters and Artificial Neural Network (ANN) models. The results show that ten models forecasting 24hour data have better performance than single models for 24 hours.

최근 정부의 친환경 정책에 따라 태양광 발전 설비가 지속적으로 증가하고 있다. 태양광 발전량은 에너지원인 태양의 특성상 계절에 따라 하루 중 발전이 이루어지는 시간이 일정하지 않다. 이러한 특성으로 인해 태양광 발전량 예측에서는 연속된 시간간격으로 수집된 자료에 적용할 수 있는 시계열 모형 적용에 어려움이 있다. 본 논문에서 제안하는 방법은 연속된 시간자료를 각 시간대 별로 분리, 재구성하여 24개의 (1시-24시) 일별 자료 형태로 예측에 활용하는 방법이다. 강원도 영암 태양광 발전소의 시간별 발전량 자료를 공공데이터포털에서 수집하여 연구하였다. 기존방법과 제안된 방법의 성능차이를 비교하기 위해 ARIMAX, 신경망(neural network model) 모형을 동일한 모형과 변수를 가지는 환경에서 성능차이를 확인하였다.

Keywords

References

  1. Cancelo, J. R., Espasa, A., and Grafe, R. (2008). Forecasting the electricity load from one day to one week ahead for the Spanish system operator, International Journal of Forecasting, 24, 588-602. https://doi.org/10.1016/j.ijforecast.2008.07.005
  2. Cottet, R and Smith, M. (2003). Bayesian modeling and forecasting of intraday electricity load, Journal of the American Statistical Association, 98, 839-849. https://doi.org/10.1198/016214503000000774
  3. Holt, C. C. (1957). Forecasting seasonals and trends by exponentially weighted moving averages, ONR Memorandum , 52. Pittsburgh, PA: Carnegie Institute of Technology. Available from the Engineering Library, University of Texas at Austin.
  4. Inman, R. H., Pedro, H. T., and Coimbra, C. F. (2013). Solar forecasting methods for renewable energy integration, Progress in Energy and Combustion Science, 39, 535-576. https://doi.org/10.1016/j.pecs.2013.06.002
  5. Kim, K. H. and Kim, J. Y. (2016). The optimal design and economic evaluation of a stand-alone RES energy system for residential, agricultural and commercial sectors, Korean Chemical Engineering Research, 54, 470-478. https://doi.org/10.9713/kcer.2016.54.4.470
  6. Lee, S. H., Kim, H. D., and Cho, C. (2014). Study on the variation characteristic of the photo-volatic power generation due to regional meteorological elements, Journal of Environmental Science International, 23, 1943-1951. https://doi.org/10.5322/JESI.2014.23.11.1943
  7. Ramanathan, R., Engle, R., Granger, C. W., Vahid-Araghi, F., and Brace, C. (1997). Short-run forecasts of electricity loads and peaks, International Journal of Forecasting, 13, 161-174. https://doi.org/10.1016/S0169-2070(97)00015-0
  8. Winters, P. R. (1960). Forecasting sales by exponentially weighted moving averages, Management Science, 6, 324-342. https://doi.org/10.1287/mnsc.6.3.324
  9. Won, J. M., Doe, G. Y., and Heo, N. R. (2011). Predict solar radiation according to forecast report, Journal of Korean Navigation and Port Research, 35, 387-392. https://doi.org/10.5394/KINPR.2011.35.5.387
  10. Yoo, H. C., Lee, G. H., and Park, S. H. (2008). Analysis of data and calculation of global solar radiation based on cloud data for major cities in Korea, Journal of the Korean Solar Energy Society, 28, 17-24.