KEPCO Journal on Electric Power and Energy

Korea Electric Power Corporation (한국전력공사)
권호 표지
DOI QR코드

DOI QR Code

Stochastic Real-time Demand Prediction for Building and Charging and Discharging Technique of ESS Based on Machine-Learning

머신러닝기반 확률론적 실시간 건물에너지 수요예측 및 BESS충방전 기법

  • Yang, Seung Kwon (KEPCO Research Institute, Korea Electric Power Corporation) ;
  • Song, Taek Ho (KEPCO Research Institute, Korea Electric Power Corporation)
  • Received : 2019.06.28
  • Accepted : 2019.07.30
  • Published : 2019.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

K-BEMS System was introduced to reduce peak load and to save total energy of the 120 buildings that KEPCO headquarter and branch offices use. K-BEMS system is composed of PV, battery, and hybrid PCS. In this system, ESS, PV, lighting is used to save building energy based on demand prediction. Currently, neural network technique for short past data is applied to demand prediction, and fixed scheduling method by operator for ESS charging/discharging is used. To enhance this system, KEPCO research institute has carried out this K-BEMS research project for 3 years since January 2016. As the result of this project, we developed new real-time highly reliable building demand prediction technique with error free and optimized automatic ESS charging/discharging technique. Through several field test, we can certify the developed algorithm performance successfully. So we will describe the details in this paper.

현재까지 피크완화 및 에너지 절감을 위해 한국전력공사 120여개 사옥에 K-BEMS (KEPCO Building Energy Management System)가 운영 중이다. 이 시스템은 PV, PCS, BESS, EMS 등으로 구성되어 있으며 건물에너지 수요예측을 기반으로 BESS, PV 등을 활용하여 에너지 관리를 도모하고 있다. 이 시스템은 단기 과거데이터에 신경망기법을 단순 적용하여 수요를 예측함에 따라 예측 정확도가 높지 않고 운영자 수작업을 통한 BESS 충방전으로 피크 저감이 곤란하며 운영 경제성 제고가 어려운 실정이다. 이러한 문제를 해결하기 위해 전력연구원에서는 2016년부터 3년간 연구과제를 수행하였는데 이를 통해 에러를 최소화하며 높은 신뢰도를 가지는 실시간 수요예측기법과 이에 기반한 BESS충방전 최적화 자동화 기술 개발, 성능을 검증하였기에 이를 본 논문에서 소개하고자 한다.

Keywords

References

  1. 기초전력연구원 전력중앙교육센터, "스마트그리드를 위한 전력저장기술", 2010.8.
  2. Editor-in-chief-Santamouris, "Advances in building Energy Research," p1-28, 2007.
  3. Kim bong suk, "전력산업 응용분야별 배터리의 경제성분석", pp. 8, 2011.10.25.
  4. Jeremy Every, Li Li, David G. Dorrell, "Optimal Selection of small scale hybrid PV battery systems to maximize economic benefit based on Tempral Load data."
  5. 수요관리실, "한국전력공사 전력수요관리 이론과 실무", 2002.11 p223-227.
  6. Shawn Fitzpatrick, P.F, Matt Murry, "Community Storage Report," Advanced Energy, January 14, pp. 6, 2011.
  7. 한국전력공사 전력연구원, "전력회사의 합리적인 수요관리 시행방안연구", pp. 215-271, 2010.4.
  8. 에너지관리공단, "DSM 프로그램별 M&V 및 경제성평가(최종보고서)", pp. 315-328, 2000.12.
  9. E. Zhou, T. Logenthiran, W. L. Woo, "Integration of a PV-Battery Hybrid System with the Main Power Grid."
  10. Kajl. S., Roberge M.A., LAMARCHE L. et al., "Evaluation of building Energy consumtion based on fuzzy logic and neural networks," 1997.
  11. KARATASOU S., SANTAMOURIS M., "Artificial neural networks in energy applications in buildings," International Journal of Low Carbon Tech, vol. 1. Pp. 201-216, 2006. https://doi.org/10.1093/ijlct/1.3.201
  12. Crawley D.B., hand J.W., Kummert M.et al., "Contrasting the capabilities of building energy performance simulation programs," Building and Environment, vol. 4.3, no. 4, pp.661-673.