Journal of the Korean Data and Information Science Society

The Korean Data and Information Science Society (한국데이터정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Evaluation of weather information for electricity demand forecasting

전력수요예측을 위한 기상정보 활용성평가

  • Shin, YiRe (WISE institute, Hankuk University of Foreign Studies) ;
  • Yoon, Sanghoo (Department of Computer Science and Statistics, Daegu University)
  • 신이레 (한국외국어대학교 차세대도시농림융합기상사업단) ;
  • 윤상후 (대구대학교 전산통계학과)
  • Received : 2016.08.16
  • Accepted : 2016.11.28
  • Published : 2016.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, weather information has been increasingly used in various area. This study presents the necessity of hourly weather information for electricity demand forecasting through correlation analysis and multivariate regression model. Hourly weather data were collected by Meteorological Administration. Using electricity demand data, we considered TBATS exponential smoothing model with a sliding window method in order to forecast electricity demand. In this paper, we have shown that the incorporation of weather infromation into electrocity demand models can significantly enhance a forecasting capability.

오늘날 기상정보는 도로공학, 경제학, 환경공학 등 다양한 분야에 활용되고 있다. 본 연구는 전력수요 예측을 위한 기상정보 활용성을 평가하고자 한다. 기상변수는 기상관측소에서 수집되는 기온, 풍속, 습도, 운량, 기압과 기온, 풍속, 상대습도의 합성지수인 체감온도와 불쾌지수가 고려되었다. 전력수요 예측을 위한 시계열모형으로 슬라이딩 창 방식의 TBATS 삼중지수평활모형이 고려되었다. 월 단위 기상변수와 전력수요 예측오차간 상관분석 결과를 보면 시간대별로 차이를 있으나 기온, 불쾌지수, 체감온도가 전력수요 예측오차와 상관성이 높았다. 이에 과거 3년의 월단위 전력수요 예측오차와 기상변수의 회귀모형식으로 전력수요 예측값의 편의를 보정하였다. 온도, 상대습도, 풍속으로 TBATS 모형의 전력수요 예측값을 보정한 결과 TBATS 모형에 비해 RMSE가 약 6.1% 줄었다.

Keywords

References

  1. Box, G. E. P. and Cox, D. R. (1964). An analysis of transformation. Journal of the Royal Statistical Society B, 26, 211-252.
  2. Cha, J., Lee, D., Kim, H. and Joo, S. K. (2015). The relationship between daily peak load and weather conditions using stepwise multiple regression. The proceedings of Korean Institute of Electrical Engineers, 475-476.
  3. De Livera, A. M., Hyndman, R. J. and Snyder, R. D. (2011). Forecasting time series with complex seasonal patterns using exponential smoothing. Journal of the American Statistical Association, 106, 1513-1527. https://doi.org/10.1198/jasa.2011.tm09771
  4. Cui, H. and Peng, X. (2015). Short-term city electric load forecasting with considering temperature effects : An improved ARIMAX model. Mathematical Problems in Engineering, Available from http://dx.doi.org/10.1155/2015/589374.
  5. Lee, Y. S., Kim, J., Jang, M. S. and Kim, H. G. (2013). A study on comparing short-term wind power prediction models in Gunsan wind farm. Journal of the Korean Data & Information Science Society, 24, 585-592. https://doi.org/10.7465/jkdi.2013.24.3.585
  6. Lim, J. H., Kim, S. Y., Park, J. D. and Song, K. B. (2013). Representative temperature assessment for improvement of short-term load forecasting cccuracy. Journal of the Korean Institute of Illuminating and Electrical Installation Engineers, 27, 39-43.
  7. Kim, C. H. (2013a). Electricity demand patterns analysis by daily and timely time series. Korea Development Institute, 13-03, Sejong, Korea.
  8. Kim, C. H. (2013b). Short-term electricity demand forecasting using complex seasonal exponential smoothing. Korea Development Institute, 13-06, Sejong, Korea.
  9. Kim, C. H. (2014). Electricity demand forecasting using mixed data sampling model. Korea Development Institute, 13-06, Sejong, Korea.
  10. 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
  11. Shin, D. and Jo, H. (2014). A empirical study on the climate factor sensitivity and threshold temperature of daily maximum electricity consumption in Korea. Korea Economic and Business Association, 32, 175-212.
  12. Shin, Y. and Yoon, S. (2016). Electricity forecasting model using specific time zone. Journal of the Korean Data & Information Science Society, 27, 275-284. https://doi.org/10.7465/jkdi.2016.27.2.275
  13. Taylor, J. W. and Buizza, R. (2003). Using weather ensemble predictions in electricity demand forecasting. International Journal of Forecasting, 19, 57-70. https://doi.org/10.1016/S0169-2070(01)00123-6
  14. Taylor, J. W. (2010). Triple seasonal methods for short-term electricity demand forecasting. European Journal of Operational Research, 204, 139-152. https://doi.org/10.1016/j.ejor.2009.10.003
  15. Yoon, S. and Choi, Y. (2015). Functional clustering for electricity demand data: A case study. Journal of the Korean Data & Information Science Society, 26, 885-894. https://doi.org/10.7465/jkdi.2015.26.4.885

Cited by

  1. A Study on the Suitability of Load Demand Forecasting Models for Island Area Using Weather Variables vol.13, pp.2, 2017, https://doi.org/10.7849/ksnre.2017.6.13.2.084