DOI QR코드

DOI QR Code

스마트그리드 환경하의 가정용 AMI 자료를 위한 시계열 군집분석 연구

Time series clustering for AMI data in household smart grid

  • 이진영 (중앙대학교 응용통계학과) ;
  • 김삼용 (중앙대학교 응용통계학과)
  • Lee, Jin-Young (Department of Applied Statistics, Chung-Ang University) ;
  • Kim, Sahm (Department of Applied Statistics, Chung-Ang University)
  • 투고 : 2020.09.14
  • 심사 : 2020.10.23
  • 발행 : 2020.12.31

초록

스마트그리드 환경하에서 ICT 기술의 발달로 AMI 기기를 통해 가정의 실시간 전력사용량을 수집할 수 있게 됨에 따라 이러한 자료들을 활용하여 보다 더 정확한 가정용 전력사용량 예측을 할 수 있게 되었다. 본 논문에서는 1시간 단위 가정용 전력사용량 자료를 바탕으로 ARIMA, TBATS, NNAR 모형을 사용하여 전력수요를 예측하는 모형을 연구하였는데, 기존과 달리 가구 전체 사용량을 한 번에 예측하는 것이 아닌 유사한 전력사용패턴을 나타내는 가구들을 군집하여 군집별로 예측 모형을 수립하고 각 모형별 예측치를 합산하여 예상 전력사용량을 산출하였다. 특히 전력사용량 자료는 전형적인 시계얼 자료로서 군집분석 방법으로 시계열에 적절한 방법을 선택하였으며 본 논문에서는 동적타임워핑(dynamic time warping)과 Periodogram 기반의 방법을 사용하였다. 연구 결과 사용량이 유사한 가구들을 군집하여 전력사용량을 예측하는 것이 한 번에 예측하는 것보다 예측 성능이 더 우수한 것으로 나타났으며 예측 모형 중에서는 여름철의 경우 NNAR 모형이, 겨울철의 경우 TBATS 모형의 성능이 가장 좋았으며 군집분석 방법은 군집 간 패턴의 차이가 명확히 나타난 동적타임워핑 방법을 사용했을 때 예측 성능의 향상이 가장 많았다.

Residential electricity consumption can be predicted more accurately by utilizing the realtime household electricity consumption reference that can be collected by the AMI as the ICT developed under the smart grid circumstance. This paper studied the model that predicts residential power load using the ARIMA, TBATS, NNAR model based on the data of hour unit amount of household electricity consumption, and unlike forecasting the consumption of the whole households at once, it computed the anticipated amount of the electricity consumption by aggregating the predictive value of each established model of cluster that was collected by the households which show the similiar load profile. Especially, as the typical time series data, the electricity consumption data chose the clustering analysis method that is appropriate to the time series data. Therefore, Dynamic Time Warping and Periodogram based method is used in this paper. By the result, forecasting the residential elecrtricity consumption by clustering the similiar household showed better performance than forecasting at once and in summertime, NNAR model performed best, and in wintertime, it was TBATS model. Lastly, clustering method showed most improvements in forecasting capability when the DTW method that was manifested the difference between the patterns of each cluster was used.

키워드

참고문헌

  1. Berndt, D. J. and Clifford, J. (1994). Using dynamic time warping to find patterns in time series, In KDD workshop, 10, 359-370.
  2. Box, G. E., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control (5th ed.), John Wiley & Sons, New York.
  3. Caiado, J., Crato, N., and Pena, D. (2006). A periodogram-based metric for time series classification, Computational Statistics & Data Analysis, 50, 2668-2684. https://doi.org/10.1016/j.csda.2005.04.012
  4. Casado, D. (2010). Classification techniques for time series and functional data, Doctoral dissertation, Universidad Carlos III de Madrid
  5. 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
  6. Gajowniczek, K. and Zabkowski, T. (2014). Short term electricity forecasting using individual smart meter data, Procedia Computer Science, 35, 589-597. https://doi.org/10.1016/j.procs.2014.08.140
  7. Hyndman, R., Athanasopoulos, G., Bergmeir, C., et al. (2020). 'forecast: Forecasting functions for time series and linear models'. R package version 8.12.
  8. Hyndman R. J. and Khandakar, Y. (2008). Automatic time series forecasting: the forecast package for R, 'Journal of Statistical Software', 26, 1-22.
  9. Kong, W., Dong, Z. Y., Hill, D. J., Luo, F., and Xu, Y. (2017). Short-term residential load forecasting based on resident behaviour learning, IEEE Transactions on Power Systems, 33, 1087-1088. https://doi.org/10.1109/TPWRS.2017.2688178
  10. Kruskal, J. B. (1983). An overview of sequence comparison: Time warps, string edits, and macromolecules, SIAM review, 25, 201-237. https://doi.org/10.1137/1025045
  11. Lee, J. S., Sohn, H. G., and Kim, S. (2013). Daily peak load forecasting for electricity demand by time series models, The Korean Journal of Applied Statistics, 26, 349-360. https://doi.org/10.5351/KJAS.2013.26.2.349
  12. McLoughlin, F., Duffy, A., and Conlon, M. (2015). A clustering approach to domestic electricity load profile characterisation using smart metering data, Applied energy, 141, 190-199. https://doi.org/10.1016/j.apenergy.2014.12.039
  13. Montero, P. and Vilar, J. A. (2014). TSclust: An R Package for Time Series Clustering, Journal of Statistical Software, 62, 1-43.
  14. Quilumba, F. L., Lee, W. J., Huang, H., Wang, D. Y., and Szabados, R. L. (2014). Using smart meter data to improve the accuracy of intraday load forecasting considering customer behavior similarities, IEEE Transactions on Smart Grid, 6, 911-918. https://doi.org/10.1109/TSG.2014.2364233
  15. Shahzadeh, A., Khosravi, A., and Nahavandi, S. (2015). Improving load forecast accuracy by clustering consumers using smart meter data, In 2015 international joint conference on neural networks, 1-7.
  16. Sohn, H., Jung, S., and Kim, S. (2016). A study on electricity demand forecasting based on time series clustering in smart grid, The Korean Journal of Applied Statistics, 29, 190-203.
  17. Son, H. G., Kim, Y., and Kim, S. (2020). Time Series Clustering of Electricity Demand for Industrial Areas on Smart Grid, Energies, 13, 2377. https://doi.org/10.3390/en13092377
  18. Tureczek, A., Nielsen, P. S., and Madsen, H. (2018). Electricity consumption clustering using smart meter data, Energies, 11, 859. https://doi.org/10.3390/en11040859
  19. Wijaya, T. K., Vasirani, M., Humeau, S., and Aberer, K. (2015). Cluster-based aggregate forecasting for residential electricity demand using smart meter data, In 2015 IEEE international conference on Big data, 879-887.