DOI QR코드

DOI QR Code

태양광시스템 모델식과 기계학습을 이용한 발전성능 추정

Estimation of Power Using PV System Model Formula and Machine Learning

  • 오현규 (에너지과학기술대학원, 충남대학교) ;
  • 신우균 (태양광연구단, 재생에너지연구소, 한국에너지기술연구원) ;
  • 주영철 (태양광연구단, 재생에너지연구소, 한국에너지기술연구원) ;
  • 배수현 (태양광연구단, 재생에너지연구소, 한국에너지기술연구원) ;
  • 황혜미 (태양광연구단, 재생에너지연구소, 한국에너지기술연구원) ;
  • 강기환 (태양광연구단, 재생에너지연구소, 한국에너지기술연구원) ;
  • 고석환 (태양광연구단, 재생에너지연구소, 한국에너지기술연구원) ;
  • 장효식 (에너지과학기술대학원, 충남대학교)
  • Hyun Gyu Oh (Graduate School of Energy Science & Technology, Chungnam National University) ;
  • Woo Gyun Shin (Photovoltaics Research Department, Korea Institute of Energy Research) ;
  • Young Chul Ju (Photovoltaics Research Department, Korea Institute of Energy Research) ;
  • Soo Hyun Bae (Photovoltaics Research Department, Korea Institute of Energy Research) ;
  • Hye Mi Hwang (Photovoltaics Research Department, Korea Institute of Energy Research) ;
  • Gi Hwan Kang (Photovoltaics Research Department, Korea Institute of Energy Research) ;
  • Suk Whan Ko (Photovoltaics Research Department, Korea Institute of Energy Research) ;
  • Hyo Sik Chang (Graduate School of Energy Science & Technology, Chungnam National University)
  • 투고 : 2023.02.15
  • 심사 : 2023.03.06
  • 발행 : 2023.03.31

초록

In this paper, a machine learning model by using a regression algorithm is proposed to estimate the power generation performance of the BIPV system. The physical model formula for estimating the generation performance and the proposed model were compared and analyzed. For the physical model formula, simple efficiency model, temperature correction model, and regressive physics model for changing an irradiance were used. As a result, when comparing the regressive physics model for changing an irradiance and the proposed model with the actual generation measured data, the respective RMSE values are 0.1497 kW, 0.0451 kW and the accuracy values are 86.44%, and 96.56%. Therefore, the proposed model implemented in this experiment can be useful in estimating power generation.

키워드

과제정보

본 연구는 산업통상자원부와 한국에너지기술평가원의 지원을 받아 수행한 연구 과제입니다(No:20223030010200).

참고문헌

  1. Ministry of Trade, Industry and Energy, Renewable Energy 3020 Implementation Plan, Ministry of Trade, Industry and Energy (2017).
  2. Di Lorenzo, Gianfranco, G., Araneo, R., Mitolo, M., Niccolai, A., & Grimaccia, F., Review of O&M practices in PV plants: Failures, solutions, remote control, and monitoring tools, IEEE Journal of Photovoltaics, 10(4), 914-926 (2020). https://doi.org/10.1109/JPHOTOV.2020.2994531
  3. Klise, G., & Balfour, J. A Best Practice for Developing Availability Guarantee Language in Photovoltaic (PV) O&M Agreements, Office of Scientific and Technical Information (OSTI) (2015).
  4. Ko, S.-W., So, J.-H., Hwang, H.-M., Ju, Y.-C., Song, H.-J., Shin, W.-G., … Kang, I.-C. The Monitoring System with PV Module-level Fault Diagnosis Algorithm. Journal of the Korean Solar Energy Society. The Korean Solar Energy Society (2018, June
  5. Shin, W. G., Oh, H. G., Bae, S. H., Ju, Y. C., Hwang, H. M., & Ko, S. W. Fault Diagnosis of PV String Using Deep-Learning and I-V Curves. Current Photovoltaic Research, 10(3), 77-83 (2022). https://doi.org/10.21218/CPR.2022.10.3.077
  6. Shin, J.-Y., Ko, S.-W., Shin, W.-G., Hwang, H.-M., Ju, Y., Kang, G.-H., & Chang, H.-S. Proposal of Power Estimation Model of Color BIPV System. Journal of the Korean Solar Energy Society. The Korean Solar Energy Society (2021, October
  7. Makrides, G., Zinsser, B., Schubert, M., & Georghiou, G. E. Energy yield prediction errors and uncertainties of different photovoltaic models. Progress in Photovoltaics: Research and Applications. Wiley (2011, November 15).
  8. Roberts, J. J., Mendiburu Zevallos, A. A., & Cassula, A. M. Assessment of photovoltaic performance models for system simulation. Renewable and Sustainable Energy Reviews. Elsevier BV (2017, May).
  9. Lee, Y. K., Shin, W.-G., Ju, Y.-C., Hwang, H.-M., Kang, G.-H., Ko, S.-W., & Chang, H.-S. Estimation of PV Power Generation by Linear Regression Model Using Voltage and Current Data. Journal of the Korean Solar Energy Society. The Korean Solar Energy Society (2021, October 1).