The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Renewable Energy Generation Prediction Model using Meteorological Big Data

기상 빅데이터를 활용한 신재생 에너지 발전량 예측 모형 연구

  • Mi-Young Kang (Dept. Information & Communication Engineering, Honam University)
  • 강미영 (호남대학교 정보통신공학과)
  • Received : 2022.12.24
  • Accepted : 2023.02.17
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Renewable energy such as solar and wind power is a resource that is sensitive to weather conditions and environmental changes. Since the amount of power generated by a facility can vary depending on the installation location and structure, it is important to accurately predict the amount of power generation. Using meteorological data, a data preprocessing process based on principal component analysis was conducted to monitor the relationship between features that affect energy production prediction. In addition, in this study, the prediction was tested by reconstructing the dataset according to the sensitivity and applying it to the machine learning model. Using the proposed model, the performance of energy production prediction using random forest regression was confirmed by predicting energy production according to the meteorological environment for new and renewable energy, and comparing it with the actual production value at that time.

태양광, 풍력 등의 신재생 에너지는 기상조건 및 환경변화에 민감한 자원이다. 설치위치 및 구조에 따른 설비의 발전량이 달라질 수 있기 때문에 정확한 발전량 예측은 중요하다. 기상 빅데이터를 활용하여 주성분 분석을 기반으로 데이터 전처리 과정을 진행하여 신재생 에너지 발전량 예측 시 영향을 미치는 피처간의 관계를 모니터링하였다. 또한, 본 연구에서는 영향을 미치는 민감도에 따라 데이터셋을 재구성하여 머신러닝 모델에 적용하여 예측도를 테스트하였다. 제안한 모형을 사용하여 신재생 에너지를 대상으로 기상환경에 따라 에너지 발전량을 예측하고 해당 시점의 실제 생산 값과 비교함으로써 랜덤 포레스트 회귀 분석을 적용한 에너지 발전량 예측에 대한 성능을 확인하였다.

Keywords

Acknowledgement

본 제(결과물)는 2022년도 교육부의 재원으로 한국연구재단의 지원을 받아 수행된 지자체-대학 협력기반 지역혁신 사업의 결과입니다.(2021RIS-002)

References

  1. J. Lee, "Optimal Operation of Energy Storage Devices based on Artificial Intelligence," Journal of the Korean Soloar Energy Society, vol. 42, no. 1, Feb. 2022, pp. 155-175. https://doi.org/10.7836/kses.2022.42.1.155
  2. J. T. Dellosa and E. C. Palconit, "Artificial Intelligence(AI) in Renewable Energy Systems: A Condensed Review of its Applications and Techniques," IEEE International Conference(EEEIC/I&CPS Europe), Bari, Italy, Sept. 2021.
  3. J. Choi and H. Choi, "Prediction of Wind Power Generation using Deep Learning," J. of the Korea Institute of Electronic Communication Sciences, vol. 16, no. 02, Apr. 2021, pp. 329-338.
  4. S. Lee, S. Jung and J. Koh, "Recurrent Neural Network based Prediction System of Agricultural Photovoltaic Power Generation," J. of the Korea Institute of Electronic Communication Sciences, vol. 17, no. 05, Oct. 2022, pp. 825-832.
  5. M. Chaikumbung, "Institutions and consumer preferences for renewable energy: A meta-regression analysis," Renewable and Sustainable Energy Reviews, vol. 146, Aug. 2021, pp. 1-24. https://doi.org/10.1016/j.rser.2021.111143
  6. J. Lee and I. Lee, "Trends in ICT-based renewable energy generation prediction technology," The Journal of Korean Institute of Communications and Information Sciences, vol. 36, no. 11, Oct. 2019, pp. 3-8.
  7. D. Shin and C. Kim, "Short Term Forecast Model for Solar Power Generation using RNN-LSTM," Journal of Advanced Navigation Technology, vol. 22 no. 3, 2018, pp. 233-239. https://doi.org/10.12673/JANT.2018.22.3.233
  8. L. Martin, L. F. Zarzalejo, J. Polo, A. Navarro, R. Marchante and M. Cony, "Prediction of global solar irradiance based on time series analysis: Application to solar thermal power plants energy production panning," Solar Energy, vol. 84, no. 10, 2010, pp. 1772-1781. https://doi.org/10.1016/j.solener.2010.07.002
  9. S. Park and S. Kim, "A study on short-term wind power forecasting using time series models," The Korean Journal of Applied Statistics, vol. 29, no. 7, 2016, pp. 1373-1383. https://doi.org/10.5351/KJAS.2016.29.7.1373
  10. L. Breiman, "Random Forests," Machine Learning, vol. 45, 2001, pp. 5-32. https://doi.org/10.1023/A:1010933404324
  11. B. M. S. Hasan and A. M. Abdulazeez, "A Review of Principal Component Analysis Algorithm for Dimensionality Reduction," Journal of Soft Computing and Data Mining, vol. 2, no. 1, 2021, pp. 20-30. https://doi.org/10.30880/jscdm.2021.02.01.003