DOI QR코드

DOI QR Code

Outside Temperature Prediction Based on Artificial Neural Network for Estimating the Heating Load in Greenhouse

인공신경망 기반 온실 외부 온도 예측을 통한 난방부하 추정

  • 김상엽 (한국기계연구원 청정연료발전연구실) ;
  • 박경섭 (국립원예특작과학원) ;
  • 류근호 (충북대학교 전기전자정보컴퓨터학부)
  • Received : 2018.01.29
  • Accepted : 2018.04.04
  • Published : 2018.04.30

Abstract

Recently, the artificial neural network (ANN) model is a promising technique in the prediction, numerical control, robot control and pattern recognition. We predicted the outside temperature of greenhouse using ANN and utilized the model in greenhouse control. The performance of ANN model was evaluated and compared with multiple regression model(MRM) and support vector machine (SVM) model. The 10-fold cross validation was used as the evaluation method. In order to improve the prediction performance, the data reduction was performed by correlation analysis and new factor were extracted from measured data to improve the reliability of training data. The backpropagation algorithm was used for constructing ANN, multiple regression model was constructed by M5 method. And SVM model was constructed by epsilon-SVM method. As the result showed that the RMSE (Root Mean Squared Error) value of ANN, MRM and SVM were 0.9256, 1.8503 and 7.5521 respectively. In addition, by applying the prediction model to greenhouse heating load calculation, it can increase the income by reducing the energy cost in the greenhouse. The heating load of the experimented greenhouse was 3326.4kcal/h and the fuel consumption was estimated to be 453.8L as the total heating time is $10000^{\circ}C/h$. Therefore, data mining technology of ANN can be applied to various agricultural fields such as precise greenhouse control, cultivation techniques, and harvest prediction, thereby contributing to the development of smart agriculture.

최근, 인공신경망 모델은 예측, 수치제어, 로봇제어, 패턴인식 등의 분야에서 촉망되는 기술이다. 본 연구에서는 인공신경망 모델을 이용하여 온실 외부 온도를 예측하고 이를 온실제어에 활용하는데 목적이 있다. 예측 모델의 성능 평가를 위해 다중회귀모델과 SVM 모델과의 비교분석을 수행하였다. 평가 방법으로는 10-Fold Cross Validation을 사용하였으며, 예측 성능 향상을 위해 상관관계분석 통해 데이터 축소를 수행하였고, 측정 데이터로부터 새로운 Factor 추출하여 데이터의 신뢰성을 확보하였다. 인공신경망 구축을 위해 Backpropagation algorithm을 사용하였으며, 다중회귀모델은 M5 method로 구축하였고, SVM 모델을 epsilon-SVM으로 구축하였다. 각 모델의 비교분석 결과 각각 0.9256, 1.8503과 7.5521로 나타났다. 또한 예측모델을 온실 난방부하 계산에 적용함으로써 온실에 사용되는 에너지 비용 절감을 통한 수입증대에 기여할 수 있다. 실험한 온실의 난방부하는 3326.4kcal/h이며, 총 난방시간이 $10000^{\circ}C/h$일 때 연료소비량은 453.8L로 예측된다. 아울러 데이터 마이닝 기술 중 하나인 인공신경망을 정밀온실제어, 재배기법, 수확예측 등 다양한 농업 분야에 적용함으로써 스마트 농업으로의 발전에 기여할 수 있다.

Keywords

References

  1. S. W. Nam, H. H. Shin, and D. W. Seo "Comparative Analysis of Weather Data for Heating and Cooling Load Calculation in Greenhouse Environmental Design," Protected Horticulture and Plant Factory, Vol.23, No.3, pp.174-180, 2014. https://doi.org/10.12791/KSBEC.2014.23.3.174
  2. M. Trejo-Perea, G. Herrera-Ruiz, J. Rios-Moreno, R. C. Miranda, and E. Rivas-Araiza, "Greenhouse Energy Consumption Prediction using Neural Networks Models," International Journal of Agriculture & Biology, Vol.1, No.1, p.1-6, 2009.
  3. H. Yu, Y. Chen, S. G. Hassan, and D. Li, "Prediction of the temperature in a Chinese solar greenhouse based on LSSVM optimized by improved PSO," Computers and Electronics in Agriculture, Vol.122, pp.94-102, 2016. https://doi.org/10.1016/j.compag.2016.01.019
  4. B. Khoshnevisan, S. Rafiee, and H. Mousazadeh, "Application of multi-layer adaptive neuro-fuzzy inference system for estimation of greenhouse strawberry yield," Measurement, Vol.47, pp.903-910, 2014. https://doi.org/10.1016/j.measurement.2013.10.018
  5. S. Y. Kim, S. M. Lee, K. S. Park, K. H. Ryu, "Prediction Model of Internal Temperature using Backpropagation Algorithm for Climate Control in Greenhouse," Horticultural Science and Technology, to be submitted, 2018.
  6. I. Guyon, and A. Elisseeff, "An Introduction to Variable and Feature Selection," Journal of Machine Learning Research, pp.1157-1182, 2003.
  7. R. Kohavi, "A study of Cross-Valiation and Bootstrap for Accuracy Estimation and Model Selection," International Joint Conference on Artificial Intelligence, 1995.
  8. G. Zhang, B. E. Patuwo, and M. Y. Hu, "Forecasting with artificial neural networks: The state of the art," International Journal of Forecasting, 1998.
  9. L. STravs, and M. Brilly, "Development of a low-flow forecasting model using the M5 machine learning method," Hydrological Sciences Journal, Vol.52, no. 3, pp.466-477, 2007. https://doi.org/10.1623/hysj.52.3.466
  10. R. Pelossof, A. Miller, P. Allen, and T. Jebara, "An SVM learning approach to robotic grasping," IEEE International Conference, Vol.4, pp.3512-3518, 2004.
  11. A. Mucherino, P. Papajorgji, and P. M. Pardalos, "A survey of data mining techniques applied to agriculture," Operational Research, Vol.9, No.2, pp.121-140, August 01, 2009. https://doi.org/10.1007/s12351-009-0054-6