Journal of the Korean Data Analysis Society

Korean Data Analysis Society (한국자료분석학회)
권호 표지

Development of Building Electricity Load Forecasting Algorithm for Economic EMS Operations

경제적 EMS 운영을 위한 건물 전력부하 예측 알고리즘 개발

  • Lee, Sunghee (Department of Consulting, E3 EXPERT Inc.) ;
  • Hwang, Hyemi (Photovoltaic Laboratory, Korea Institute of Energy Research) ;
  • Park, Yonggi (Department of Electrical Engineering, Konkuk University) ;
  • Park, Jongbae (Department of Electrical Engineering, Konkuk University) ;
  • Moon, Sungho (Department of Data Management, Busan University of Foreign Studies)
  • 이성희 ((주)E3 EXPERT) ;
  • 황혜미 (한국에너지기술연구원 태양광연구실) ;
  • 박용기 (건국대학교 공과대학 전기공학과) ;
  • 박종배 (건국대학교 공과대학 전기공학과) ;
  • 문승호 (부산외국어대학교 상경대학 데이터경영학과)
  • Received : 2014.08.11
  • Accepted : 2014.10.01
  • Published : 2014.10.31
⟨ Previous Next ⟩

Abstract

The dissemination of energy management system (EMS), which uses renewable energies and energy storage system, is expanded for buildings. The very important point of EMS operation is to forecast a power load for buildings with estimating an accurate power load consumption pattern. Generally, existing methods of load forecasting have statistically and mathematically proposed the complicated and variety methodologies. But, the forecasting methods should quickly provide the results, and have to consider the convenience of operation to apply the management system. In particular, the methodology has to supply a environment that the operator can quickly be reflected the change factor of power load. This study draws the electrical load pattern for a building of the Korea Institute of Energy Research (KIER) through the precedent study about a forecasting methodology of electrical loads, and suggests the forecasting results for the same load by modifying a load pattern of the building using the same forecasting methodology as precedent study.

신재생에너지의 보급과 에너지 저장장치를 활용한 건물 에너지관리시스템(BEMS, building energy management system)의 보급이 확대되고 있다. 이러한 에너지관리시스템에서 매우 중요한 관리 대상은 정확한 부하 사용 패턴을 파악하여 건물의 전력 부하를 예측하는 것이다. 기존 전력부하의 예측방법론은 일반적으로 예측 정확도를 향상시키기 위해 복잡하고 다양한 통계적, 수리적 방법론을 제안하고 있다. 그러나 시스템의 적용을 위해서는 빠른 시간내에 예측결과의 제공이 가능하고 운영의 편의성이 고려되어야 하며, 특히 운영자가 전력부하의 변경요인을 신속하게 반영하기 위한 환경이 매우 중요하다. 따라서 본 논문에서는 전력부하의 예측 방법론에 대한 선행연구를 통해 한국에너지기술연구원 한 연구동의 전력부하 패턴을 도출하였고 이 절차를 그대로 활용하여 원내 건물에 전력부하 패턴을 수정하여 부하 예측을 수행한 결과를 제시한다.

Keywords

Acknowledgement

Supported by : 한국에너지기술연구원

References

  1. Choi, S. Y., Kim, H. J. (2007). Short-term Demand Forecasting Using Data Mining Method, Journal of Korean Institute of Illuminating and Electrical Installation Engineers, 21(10), 126-133. (in Korean).
  2. KIER (Korea Institute of Energy Research) (2013). Establishment of The Foundation of Technology for Industrialization.
  3. Koo, B. G., Kim, C. H., Park, J. H., Lee, H. S. (2009). Daily Electric Load Classification Using Data Mining, Proceeding of KIEE 2009 Summer, 111-112. (in Korean).
  4. KPX(Korea Power Exchange) (2011). Electricity Market Rules.
  5. Lee, S. H., Kang, H. C., Choi, H. S., Han, S. T. (2012). Customer Segmentation by Using Two-step Cluster Analysis, Journal of the Korean Data Analysis Society, 14(4), 1849-1860. (in Korean).
  6. Lee, J. S., Son, H. G., Kim, S. Y. (2013). Daily Peak Load Forecasting for Electricity Demand by Time Series Models, The Korean Journal of Applied Statistics, 26(2), 349-360. (in Korean). https://doi.org/10.5351/KJAS.2013.26.2.349
  7. Park, Y. J., Ha, M. R., Kim, U. H., Choi, H. U., Park, S. B., Joo, Y. S. (2012). Cluster Analysis of U.S. City Temperature Profiles using Mixture Model, Journal of the Korean Data Analysis Society, 14(1), 541-553. (in Korean).
  8. Park, J. D., Song, K. B. (2013). Short-Term Load Forecast for Summer Special Light-Load Period, The Transactions of the Korean Institute of Electrical Engineers, 62(4), 482-488. (in Korean). https://doi.org/10.5370/KIEE.2013.62.4.482
  9. Park, J. D., Song, K. B., Lim, H. W., Park, H. S. (2012). Short-Term Load Forecast for Near Consecutive Holidays Having The Mixed Load Profile Characteristics of Weekdays and Weekends, The Transactions of the Korean Institute of Electrical Engineers, 61(12), 1765-1773. (in Korean). https://doi.org/10.5370/KIEE.2012.61.12.1765
  10. Piao, M. H., Park, J. H., Lee, H. K., Ryu, K. H. (2008). Classification Methods for Automated Prediction of Power Load Patterns, Proceeding of Korea Computer Congress, 35(1)(C), 26-30.
  11. Son, K. T., Jung, U. K. (2012). Statistical Forecast Models of Cooling Degree Days Index, Journal of the Korean Data Analysis Society, 14(5), 2397-2407. (in Korean).
  12. Wi, Y. M., Song, K. N., Joo, S. K. (2009). Data Mining Technique Using the Coefficient of Determination in Holiday Load Forecasting, The Transactions of the Korean Institute of Electrical Engineers, 58(1), 18-22. (in Korean).
  13. Yang, J. M., Yoo, S. H. (2008). Electricity Demand Forecasts in View of Demand Management Effects, Journal of the Korean Data Analysis Society, 10(5B), 2755-2765. (in Korean).
  14. Yang, J. M., Yoo, S. H., Park, C. S. (2011). Energy Relative Prices and Electricity Demand, Journal of the Korean Data Analysis Society, 13(1B), 403-413. (in Korean).