Energy Consumption and Heat Storage in a Solar Greenhouse: Artificial Neural Network Method

In this study, the performance of a solar greenhouse heating system equipped with a linear parabolic concentrator and a dual-purpose flat plate solar collector‏ was investigated using the Artificial Neural Network (ANN) method. The heat required for the greenhouse at night hours was supplied by the heat stored in the storage tank by the solar system during the sunshine time and  an auxiliary heater. A water pump was used to make a forced-flow through the concentrator assembly. While, a natural water flow occurred in the flat plate collector. ANN method was used to predict  the tank temperature and energy consumption from the heat storage tank and by the auxiliary heater. Network inputs were solar radiation intensity, ambient temperature, wind speed, collector surface temperature, greenhouse temperature, flow rate and time. About 80% of total data were used for training, 10% for testing and 10% for validation. The results indicated that the network topology of 7-15-1 with R² and MSE of respectively 0.98 and 0.00017 presented the best results for prediction of energy consumption from the tank. While the most suitable description for variations of energy consumption by the auxiliary heater and from storage tank was given by the network topologies‏ of 7-10-10-1 (with R² of 0.99 and MSE of 0.00014) and 7-5-15-1 (with R² 0.98 of MSE  of 0.00011), respectively.