DOI QR코드

DOI QR Code

인공 신경망 회귀 모델을 활용한 인버터 기반 태양광 발전량 예측 알고리즘

Inverter-Based Solar Power Prediction Algorithm Using Artificial Neural Network Regression Model

  • 박건하 (순천대학교 컴퓨터공학과) ;
  • 임수창 (순천대학교 컴퓨터공학과) ;
  • 김종찬 (순천대학교 컴퓨터공학과)
  • 투고 : 2024.02.03
  • 심사 : 2024.04.12
  • 발행 : 2024.04.30

초록

본 논문은 전라남도에서 측정한 태양광 발전 데이터를 기반으로 발전량 예측값을 도출하기 위한 연구이다. 발전량 측정을 위해 인버터에서 직류, 교류, 환경데이터와 같은 다변량 변수를 측정하였고, 측정값의 안정성과 신뢰성 확보를 위한 전처리 작업을 수행하였다. 상관관계 분석은 부분자기상관함수(PACF: Partial Autocorrelation Function)을 활용하여 시계열 데이터에서 발전량과 상관성이 높은 데이터만을 예측을 위해 사용하였다. 태양광 발전량 예측을 위해 딥러닝 모델을 이용하여 발전량을 측정했고, 예측 정확도를 높이기 위해 각 다변량 변수의 상관관계 분석 결과를 이용하였다. 정제된 데이터를 활용한 학습은 기존 데이터를 그대로 사용했을 때 보다 안정되었고, 상관관계 분석 결과를 반영하여 다변량 변수 중 상관성이 높은 변수만을 활용하여 태양광 발전량 예측 알고리즘을 개선하였다.

This paper is a study to derive the predicted value of power generation based on the photovoltaic power generation data measured in Jeollanam-do, South Korea. Multivariate variables such as direct current, alternating current, and environmental data were measured in the inverter to measure the amount of power generation, and pre-processing was performed to ensure the stability and reliability of the measured values. Correlation analysis used only data with high correlation with power generation in time series data for prediction using partial autocorrelation function (PACF). Deep learning models were used to measure the amount of power generation to predict the amount of photovoltaic power generation, and the results of correlation analysis of each multivariate variable were used to increase the prediction accuracy. Learning using refined data was more stable than when existing data were used as it was, and the solar power generation prediction algorithm was improved by using only highly correlated variables among multivariate variables by reflecting the correlation analysis results.

키워드

참고문헌

  1. G. Bang, "Problems in Hydrogen Economy and the Need for the Development of New Energy Source," Journal of the Korean Psychiatric Association, vol. 13, no. 1, pp. 73-80 ,2009.
  2. J. Song, Y. Jeong, and S. Lee, "Analysis of prediction model for solar power generatio," Journal of digital convergence, vol. 12, no. 3, pp. 243-248, 2014. https://doi.org/10.14400/JDC.2014.12.3.243
  3. J. Hong, J. Park, and Y. Kim, "Fault Prediction of Photovoltaic Monitoring System based on Power Generation Prediction Model," Journal of Platform Technology, vol. 6, no. 2, pp. 19-25, 2018.
  4. L. Gutierrez, J. Patino, and E. G. Eduardo, "A Comparison of the Performance of Supervised Learning Algorithms for Solar Power Prediction," Energies, vol. 14, no. 15, pp. 4424, 2021.
  5. M. Han, J. Woo, and J. Lee, "Power Generation Change According to Angle Control of Solar Power Plant Panel," Journal of the KIECS, vol. 14, no. 4, pp. 685-692, 2019. https://doi.org/10.1007/s42835-019-00110-3
  6. S. Jung. J. Koh, S. Lee, "Recurrent Neural Network based Prediction System of Agricultural Photovoltaic Power Generation," Journal of the KIECS, vol. 17, no. 5, pp. 825-832, 2022.
  7. H. Long, Z. Zhang, and Y. Su, "Analysis of daily solar power prediction with data-driven approaches," Applied Energy, vol. 126, pp. 29-37, 2014. https://doi.org/10.1016/j.apenergy.2014.03.084
  8. V. Prema and K. U. Rao, "Development of statistical time series models for solar power prediction," Renewable energy, vol. 83, pp. 100-109, 2015. https://doi.org/10.1016/j.renene.2015.03.038
  9. J. Kim, "Deep Learning Model based on Imaging Time Series Data for Demand Forecasting," Doctoral dissertation, Hanyang University, 2023.
  10. J. Zhang and K. F. Man, "Time series prediction using RNN in multi-dimension embedding phase space," SMC'98 Conference Proceedings 1998 IEEE International Conference on Systems, vol. 2, no. 98CH36218, pp. 1868-1873, 1998.
  11. B. Kim, S. Jung, M. Kim, J. Kim, H. Lee, and S. Kim, "Solar Power Generation Forecasting based on LSTM considering Weather Conditions," Journal of Korean Institute of Intelligent Systems, vol. 30, no. 1, pp. 7-12, 2020. https://doi.org/10.5391/JKIIS.2020.30.1.7
  12. D. O'Leary and J. Kubby, "Feature Selection and ANN Solar Power Prediction," Journal of Renewable Energy, vol. 2017, pp. 1-7, 2017.
  13. E. Izgi, A. Oztopal, B. Yerli, M. K. Kaymak, and A. D. Sahin, "Short-mid-term solar power prediction by using artificial neural networks," Solar Energy, vol. 86, no.2, pp. 725-733, 2012. https://doi.org/10.1016/j.solener.2011.11.013