DOI QR코드

DOI QR Code

Temporal Classification Method for Forecasting Power Load Patterns From AMR Data

  • Lee, Heon-Gyu (Database/Bioinformatics Lab., School of Electrical & Computer Engineering, Chungbuk National University) ;
  • Shin, Jin-Ho (Power Information Technology Group, Korea Electric Power Research Institute) ;
  • Park, Hong-Kyu (Database/Bioinformatics Lab., School of Electrical & Computer Engineering, Chungbuk National University) ;
  • Kim, Young-Il (Power Information Technology Group, Korea Electric Power Research Institute) ;
  • Lee, Bong-Jae (Power Information Technology Group, Korea Electric Power Research Institute) ;
  • Ryu, Keun-Ho (Database/Bioinformatics Lab., School of Electrical & Computer Engineering, Chungbuk National University)
  • Published : 2007.10.31

Abstract

We present in this paper a novel power load prediction method using temporal pattern mining from AMR(Automatic Meter Reading) data. Since the power load patterns have time-varying characteristic and very different patterns according to the hour, time, day and week and so on, it gives rise to the uninformative results if only traditional data mining is used. Also, research on data mining for analyzing electric load patterns focused on cluster analysis and classification methods. However despite the usefulness of rules that include temporal dimension and the fact that the AMR data has temporal attribute, the above methods were limited in static pattern extraction and did not consider temporal attributes. Therefore, we propose a new classification method for predicting power load patterns. The main tasks include clustering method and temporal classification method. Cluster analysis is used to create load pattern classes and the representative load profiles for each class. Next, the classification method uses representative load profiles to build a classifier able to assign different load patterns to the existing classes. The proposed classification method is the Calendar-based temporal mining and it discovers electric load patterns in multiple time granularities. Lastly, we show that the proposed method used AMR data and discovered more interest patterns.

Keywords

References

  1. Huang S. J. and Shih K. R., 2003. Short-term load forecasting via ARMA model identification including non-Gaussian process considerations. IEEE Trans. Power System, 18(2): 673-679 https://doi.org/10.1109/TPWRS.2003.811010
  2. Pitt B. and Kirchen D., 1999. applications of data mining techniques to load profiling. In Proc. IEEE PICA, pp. 131-136
  3. Amjady N., 2001. Short-term hourly load forecasting using time-series modeling with peak load capability. IEEE Trans. Power System, 16(3): 498-505 https://doi.org/10.1109/59.932287
  4. Li Y. and Ning P., 2001. Discovering Calendar-based Temporal Association Rules, In Proc. of the 8th Int'l Symposium on Temporal Representation and Reasoning
  5. Jain A. K. and Dubes R. C., 1988. Algorithms for Clustering Data. Englewood Cliffs, NJ: Prentice-Hall
  6. Park H. K., Kim Y., Park J. H., and Ryu K. H., 2007. Cluster Analysis for Region Electric Load Forecasting System. to be appeared in Int'l Symposium Remote Sensing 2007
  7. Liu B. and Ma Y., 1998, Integrating classification and association rule mining. In Proc. of the 4th Int'l Conf. Knowledge Discovery and Data Mining
  8. Agrawal R. and Srikant R., 1994. Fast algorithms for mining association rules. In Proc. of the 20th VLDB Conference, pp 487-499
  9. Ernoult M., 1982. Analysis and forecast of electrical energy demand. Revue General d'Electricite, No. 4
  10. Fayyad U. M. and Irani K. B., 1993. Multi-Interval discretization of continuous-valued attributes for classification learning. In Proc. of the 13th Int'l Joint Conf. on Artificial Intelligence, pp. 1022-1027