Author:
Ghiat Ikhlas,Al-Ansari Tareq
Abstract
Abstract
Predicting energy consumption in agricultural greenhouses is essential to effectively allocate resources, enhance plant growth, and minimize energy inefficiencies. Various factors affect the energy consumption inside the greenhouse including external climate conditions and internal microclimate. Proper understanding of these factors is crucial for maintaining an ideal growing environment and optimizing energy efficiency. This drives the need to investigate the interaction between these factors and greenhouse energy consumption, encompassing the energy needed for cooling and the supply of water and nutrients. This work aims at developing a dynamic model that predicts the total energy consumption of a closed agricultural greenhouse to improve microclimate control and energy efficiency. The study is conducted within a closed-loop agricultural greenhouse with no natural ventilation. Inside, the air is cooled and continuously circulated without being exchanged with ambient air through a heating, ventilation, and air conditioning (HVAC) system. The data-driven model encompasses external climate parameters such solar radiation, ambient temperature, and relative humidity; along with microclimate parameters such as internal temperature, humidity, and CO2 concentration to predict overall energy consumption. The study examines two machine learning models, deep neural networks (DNN) and extreme gradient boosting (XGBoost), for forecasting energy consumption, and assesses their performance using the coefficient of determination (R2), the root mean square error (RMSE), and the mean absolute error (MAE). Results reveal that the DNN model surpasses the XGBoost model, exhibiting a superior predictive performance with an R2 of 80.9%, RMSE of 171.1 kWh and MAE of 130.3 kWh. This study demonstrates its practicality in assisting with energy consumption analyses and identifying inefficient energy usage patterns within closed agricultural greenhouses.