DOI QR코드

DOI QR Code

신재생 에너지 최적 활용을 위한 축열조 온도 예측 모델 연구

A Study on the Thermal Prediction Model cf the Heat Storage Tank for the Optimal Use of Renewable Energy

  • 오한별 (순천대학교 정보통신공학과) ;
  • 장경민 (순천대학교 정보통신공학과) ;
  • 오지영 ;
  • 이명배 (순천대학교 정보통신공학전공 ) ;
  • 박장우 (순천대학교 인공지능공학부 ) ;
  • 조용윤 (순천대학교 인공지능공학부 ) ;
  • 신창선 (순천대학교 인공지능공학부 )
  • 투고 : 2023.10.31
  • 심사 : 2023.11.24
  • 발행 : 2023.11.30

초록

최근 스마트팜 에너지 비용 중 35% 낸난방비 에너지 소비가 증가되어 에너지 소비 효율화가 요구되며, 전기료 현실화에 대한 우려로 신재생 에너지 중요성이 증가하고 있다. 신재생 에너지는 수력, 풍력, 태양광 등에 속하며, 이중 태양광 에너지는 전기에너지로 변환하는 발전기술로, 이 기술은 에너지원이 환경에 미치는 영향이 적고, 유지 보수가 간편하다는 특징을 갖고 있다. 본 연구에서는 온실 축열조, 히트펌프 데이터 기반으로 축열조 영향을 많이 미치는 요소를 선정하고 축열조 공급 온도예측 모델을 개발하고자 한다. 시계열 데이터 분석 및 예측에 효과적인 LSTM(Long Short-Term Memory)과 다른 앙상블 학습 기법보다 뛰어난 XGBoost 모델을 이용하여 예측한다. 히트펌프 축열조 온도를 예측함으로써 에너지 소비를 최적화하여 시스템 운영을 최적화할 수 있다. 또한, 태양광 활용에 따른 냉난방비 절감 및 농가의 에너지 자립도 개선 등 스마트팜 에너지 통합 운영 시스템에 연계하고자 한다. 플랫폼을 통해 폐열 에너지의 공급을 관리하고 최대 난방부하 및 계절, 시간별 작물생장에 필요한 에너지값을 도출하여 이를 기반으로 최적 에너지 운용방안을 도출하고자 한다.

Recently, energy consumption for heating costs, which is 35% of smart farm energy costs, has increased, requiring energy consumption efficiency, and the importance of new and renewable energy is increasing due to concerns about the realization of electricity bills. Renewable energy belongs to hydropower, wind, and solar power, of which solar energy is a power generation technology that converts it into electrical energy, and this technology has less impact on the environment and is simple to maintain. In this study, based on the greenhouse heat storage tank and heat pump data, the factors that affect the heat storage tank are selected and a heat storage tank supply temperature prediction model is developed. It is predicted using Long Short-Term Memory (LSTM), which is effective for time series data analysis and prediction, and XGBoost model, which is superior to other ensemble learning techniques. By predicting the temperature of the heat pump heat storage tank, energy consumption may be optimized and system operation may be optimized. In addition, we intend to link it to the smart farm energy integrated operation system, such as reducing heating and cooling costs and improving the energy independence of farmers due to the use of solar power. By managing the supply of waste heat energy through the platform and deriving the maximum heating load and energy values required for crop growth by season and time, an optimal energy management plan is derived based on this.

키워드

과제정보

This research was supported by "Regional Innovation Strategy (RIS)" through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(MOE)(2021 RIS-002)

참고문헌

  1. Kweon Seungll, Kang SanGgil, 'Prediction of solar power generation using XGBoost-LSTM Ensemble," Journal of Korean Institute of Intelligent Systems, Vol 31, No 6, pp. 475-479, Dec. 2021  https://doi.org/10.5391/JKIIS.2021.31.6.475
  2. Seolryung Jung, Kyoungwook Park, Jingwang Koh, Sungkeun Le, "Photovoltaic Prediction System based on Recurrent Neural Network", 2021 Korea Information, Precoessing Society, Vol 28, No 2, pp. 849-852, Nov 2021 
  3. Is Smart Farm really sustainable and ESG-appropriate agriculture(2023), https://www.impacton.net/news/articleView.html?idxno=5895, (accessed Nov., 19, 2023). 
  4. M Schuster and K.K. Paliwal, "Bidirectional Recurrent Neural Networks," Journal of In -stitute of Electrical and Electronics Engi-neers Transactions on, Signal Processing, Vol, 45, No. 11, pp. 2673-2681, 1997.  https://doi.org/10.1109/78.650093
  5. Understanding LSTM Networks, http://colah.github.io, Nov, 2017, (accessed Oct., 24, 2023). 
  6. How to Develop a Bidirectional LSTM For Sequence Classification in Python with Keras, https://machinelearningmastery.com, Nov. 2017 (accessed Oct., 29, 2023). 
  7. Junyong Jun, Soyoun Hwang, Youngmi Yoon, "A Verification about the Formation Process of Filter Bubble with Personalization Algorithm" Journal of Korea Multimedia Society, Vol. 21, No. 3, pp. 369-381, Mar. 2018.  https://doi.org/10.9717/KMMS.2018.21.3.369
  8. Natekin, Alexey and Alois Knoll "Gradient boost-ing machines, a tutorial," Frontiers in neuro-robotics, vol. 7. pp. 21, Dec. 2013. 
  9. Kwon Soo,-Hee, Ha Il Do, Na MyungHwan, "Prediction of smart farm tomato harvest time: Comparison of machine learning and deep learning approaches," Journal of the Korean Data & Information Science Society, Nol 33, No 2, pp. 283-298, Mar. 2022  https://doi.org/10.7465/jkdi.2022.33.2.283
  10. Yurim Lee, Hyunjin Kim, Dahan Lee, Chaijung Lee, Duehee Lee, "Validation of Forecasting Performance of Two-Stage Probabilistic Solar Irradiation and Solar Power Forecasting Algorithm using XGBoost," The Transactions of the Korean Institute of Electrical Engineers, vol. 68, no.12, pp. 1704-1710, Dec. 2022.  https://doi.org/10.5370/KIEE.2019.68.12.1704
  11. Joonhyeok Choi, Jongtae Lin, JaeSoo Yoo, "Prediction of Solar Power Generation Based on LSTM Considering Facility Data and Weather Data," The Journal of the Korea Contents Association, Vol 23, No 5, pp. 150-157, Mar. 2023. https://doi.org/10.5392/JKCA.2023.23.05.150