본문 바로가기
KERD
논문KCI 등재

누적 데이터 부족 시 활용 가능한 로컬 일사 예측 모델 개발 및 평가

Performance Evaluation of LSTM Based Solar Irradiance Prediction Models without Long-term Local Weather Data

김의종|전병기
한국태양에너지학회 (The Korean Solar Energy Society)|2023.10|한국태양에너지학회 논문집 (Journal of The Korean Solar Energy Society)|제43권 제5호|pp. 43-59

1

조회

0

다운로드

0

인용

0

참고문헌

키워드

LSTM모델예측제어Model predictive control기상예측Weather prediction태양 일사Solar irradianceLong term short term memory
주제분류기타공학

초록

Prediction of solar irradiance that influences the building load and production of new andrenewable energy is crucial in the predictive control of buildings. However, most solarirradiance prediction models are developed using weather data measured over a long term in thetarget region. This study proposed a solar irradiance prediction model based on a hybrid layerthat combined a long short-term memory layer and a bi-directional long short-term memorylayer. Next, the solar irradiance of the following day was predicted using only the hourlyirradiance measured on site one day before the prediction day using a model trained with theweather data of another region. The proposed solar irradiance prediction model showed anRMSE of 69.5 W/m2, a level suitable for the predictive control of buildings. Moreover,although training data from a different region was used, the performance of the proposed modelwas similar to that of a model trained with long-term data measured in the target region.

Abstract

Prediction of solar irradiance that influences the building load and production of new andrenewable energy is crucial in the predictive control of buildings. However, most solarirradiance prediction models are developed using weather data measured over a long term in thetarget region. This study proposed a solar irradiance prediction model based on a hybrid layerthat combined a long short-term memory layer and a bi-directional long short-term memorylayer. Next, the solar irradiance of the following day was predicted using only the hourlyirradiance measured on site one day before the prediction day using a model trained with theweather data of another region. The proposed solar irradiance prediction model showed anRMSE of 69.5 W/m2, a level suitable for the predictive control of buildings. Moreover,although training data from a different region was used, the performance of the proposed modelwas similar to that of a model trained with long-term data measured in the target region.

참고문헌 (43)

  1. Ferreira, P. M., "Neural Networks Based Predictive Control for Thermal Comfort and Energy Savings in Public Buildings", Energy and Buildings, 55, pp.238~251 (2012)
  2. Huang, H., "A New Model Predictive Control Scheme for Energy and Cost Savings in Commercial Buildings : An Airport Terminal Building Case Study", Building and Environment, 89, pp.203~216 (2015)
  3. Kusiak, A., "Modeling and Optimization of HVAC Energy Consumption", Applied Energy, 87(10), pp.3092~3102 (2010)
  4. Nagpal, H., "Optimal Energy Management in Smart Sustainable Buildings–A Chance-constrained Model Predictive Control Approach", Energy and Buildings, 248, pp.111163~ (2021)
  5. Nguyen, T. T., "Analyzing the Impacts of System Parameters on MPC-Based Frequency Control for a Stand-Alone Microgrid", Energies, 10(4), pp.417~ (2017)
  6. Afram, A., "Theory and Applications of HVAC Control Systems? A Review of Model Predictive Control(MPC)", Building and Environment, 72, pp.343~355 (2014)
  7. Khanmirza, E., "Predictive Control of a Building Hybrid Heating System for Energy Cost Reduction", Applied Soft Computing, 46, pp.407~423 (2016)
  8. Jeon, B. K., "Learning-Based Predictive Building Energy Model Using Weather Forecasts for Optimal Control of Domestic Energy Systems", Sustainability, 11(1), pp.147~ (2018)
  9. "Korea Meteorological administration"[URL]
  10. "National meteorological service for the UK"[URL]
  11. "The National weather service U.S"[URL]
  12. "National Meteorological service for Canada"[URL]
  13. Lago, J., "Forecasting Spot Electricity Prices : Deep Learning Approaches and Empirical Comparison of Traditional Algorithms", Applied Energy, 221, pp.386~405 (2018)
  14. Jiang, Y., "Computation of Monthly Mean Daily Global Solar Radiation in China Using Artificial Neural Networks and Comparison with Other Empirical Models", Energy, 34(9), pp.1276~1283 (2009)
  15. Sharma, V., "Short Term Solar Irradiance Forecasting Using a Mixed Wavelet Neural Network", Renewable Energy, 90, pp.481~492 (2016)
  16. Kemmoku, Y., "Daily Insolation Forecasting Using a Multi-stage Neural Network", Solar Energy, 66(3), pp.193~199 (1999)
  17. Ahmad, A., "Hourly Global Solar Irradiation Forecasting for New Zealand", Solar Energy, 122, pp.1398~1408 (2015)
  18. Benmouiza, K., "Forecasting Hourly Global Solar Radiation Using Hybrid K-means and Nonlinear Autoregressive Neural Network Models", Energy Conversion and Management, 75, pp.561~569 (2013)
  19. Li, C., "B27 : B146The Short-term Interval Prediction of Wind Power Using the Deep Learning Model with Gradient Descend Optimization", Renew Energy, 155, pp.197~ (2020)
  20. Hochreiter, S., "Long Short-Term Memory", Neural Computation, 9(8), pp.1735~1780 (1997)
  21. Qing, X., "Hourly Day-ahead Solar Irradiance Prediction Using Weather Forecasts by LSTM", Energy, 148, pp.461~468 (2018)
  22. He, H., "Probabilistic Solar Irradiance Forecasting via a Deep Learning-Based Hybrid Approach", IEEJ Transactions on Electrical and Electronic Engineering, 15, pp.1604~1612 (2020)
  23. Jeon, B. K., "Next-Day Prediction of Hourly Solar Irradiance Using Local Weather Forecasts and LSTM Trained with Non-Local Data", Energies, 13(20), pp.5258~ (2020)
  24. Rajagukguk, R. A., "A Review on Deep Learning Models for Forecasting Time Series Data of Solar Irradiance and Photovoltaic Power", Energies, 13(24), pp.6623~ (2020)
  25. Kulshrestha A, "Bayesian BILSTM Approach for Tourism Demand Forecasting", Annals of Tourism Research, 83, pp.102925~ (2020)
  26. Shahid, F., "Predictions for COVID-19 with Deep Learning Models of LSTM, GRU and Bi-LSTM", Chaos, Solitons & Fractals, 140, pp.110212~ (2020)
  27. Zhang, B., "Constructing a PM2. 5 Concentration Prediction Model by Combining Auto-Encoder with Bi-LSTM Neural Networks", Environ Model Software, 124, pp.104600~ (2020)
  28. Cheng, H., "A Hybrid Electricity Price Forecasting Model with Bayesian Optimization for German Energy Exchange", International Journal of Electrical Power & Energy Systems, 110, pp.653~ (2019)
  29. Liu, H., "Multi-objective Data-ensemble wind Speed Forecasting Model with Stacked Sparse Autoencoder and Adaptive Decomposition-based Error Correction", Applied Energy, 254, pp.113686~ (2019)
  30. Peng, T., "An Integrated Framework of Bi-directional Long-Short Term Memory(BiLSTM)Based on Sine Cosine Algorithm for Hourly Solar Radiation Forecasting", Energy, 221, pp.119887~ (2021)
  31. Jaihuni, M., "A Novel Recurrent Neural Network Approach in Forecasting Short Term Solar Irradiance", ISA Transactions, 121, pp.63~74 (2022)
  32. Graves, A., "Speech Recognition with Deep Recurrent Neural Networks", Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (2013), IEEE
  33. Fischer, T., "Deep Learning with Long Short-term Memory Networks for Financial Market Predictions", European Journal of Operational Research, 270(2), pp.654~669 (2018)
  34. Salman, A. G., "Single Layer & Multi-layer Long Short-term Memory(LSTM)Model with Intermediate Variables for Weather Forecasting", Procedia Computer Science, 135, pp.89~98 (2018)
  35. Sun, Q., "Predicting Blood Glucose with an LSTM and Bi-LSTM Based Deep Neural Network", 2018 14th Symposium on Neural Networks and Applications (NEUREL), pp.1~5 (2018), IEEE
  36. Huang, Z., "Bidirectional LSTM-CRF Models for Sequence Tagging" (2015)
  37. Xu, B., "Leveraging Biomedical Resources in Bi-LSTM for Drug-Drug Interaction Extraction", IEEE Access, 6, pp.33432~33439 (2018)
  38. MathWorks Inc., "MATLAB Documentation" (2018), MathWorks
  39. Kingma, D. P., "Adam: A Method for Stochastic Optimization" (2014)
  40. Basha, S. S., "Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification", Neurocomputing, 378, pp.112~119 (2020)
  41. ISO, "Solar Energy-specification and Classification of Instruments for Measuring Hemispherical Solar and Direct Solar Radiation", ~ (1990)
  42. Husein, M., "Day-ahead Solar Irradiance Forecasting for Microgrids Using a Long Short-term Memory Recurrent Neural Network : A Deep Learning Approach", Energies, 12(10), pp.1856~ (2019)
  43. Aslam, M., "Deep Learning Models for Long-term Solar Radiation Forecasting Considering Microgrid Installation : A Comparative Study", Energies, 13(1), pp.147~ (2019)

관련 논문AI추천

건물 예측 제어용 LSTM 기반 일사 예측 모델김의종, 이경호, 전병기한국태양에너지학회 · 한국태양에너지학회 논문집2019 · 제39권 제5호건물의 단기부하 예측을 위한 기상예측 모델 개발김의종, 이경호, 전병기한국태양에너지학회 · 한국태양에너지학회 논문집2018 · 제38권 제1호Prediction of Solar Photovoltaic Power Generation by Weather Using LSTM이샘미, 조규철한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2022 · 제27권 제8호머신 러닝 기법을 활용한 건물 에너지 사용량 예측에 관한 연구남윤광, 조성환, 최창용, 홍성기한국기계기술학회 · 한국기계기술학회지2019 · 제21권 제6호다중 지역 날씨 데이터와 양방향 LSTM을 이용한 태양광 발전 예측 및 효율적 유지보수운영 전략박능수, 안형근, 양수미한국정보처리학회 · 정보처리학회 논문지2025 · 제14권 제10호Enhancing the Performance of Solar Radiation Decomposition Models Using Deep Learning리알, 이현진한국태양에너지학회 · 한국태양에너지학회 논문집2023 · 제43권 제3호

이 간행물의 다른 논문 (6건)

국내 6개 지역 중심으로 분석한 일사량을 포함한 기상 데이터 특성김정배pp. 1-7저온 경화 은 페이스트 용 아크릴계 바인더의 다양한 개시제의 영향에 관한 연구임현수, 김성현, 남혜령, 문지연, 박고등, 전다영, Otgongerel Zulmandakh, 권오련pp. 9-17동서향으로 배치된 태양광발전시스템이 전력계통의 운용에 미치는 영향 평가 방법론 개발한규림, 김유리, 이혜선, 김용하pp. 19-32자가용 태양광설비 발전 이용률 모니터링 결과를 활용한 사후관리 조사대상 결정에 대한 연구이영섭, 박성우, 이건우, 박창대pp. 33-41지방자치단체 공유지의 태양광 발전사업 투자 유치를 위한 적정 임대료 연구강희환, 나보라, 이유선, 이호중pp. 61-67
원문 보기