Prediction of power consumption and water productivity of seawater greenhouse system using random vector functional link network integrated with artificial ecosystem-based optimization

Abstract

The seawater greenhouse desalination technology is a kind of desalination plant which simulates the water cycle through seawater evaporation and condensation into freshwater. A novel random vector functional link (RVFL) network integrated with artificial ecosystem-based optimization (AEO) algorithm is proposed to predict the performance of the seawater greenhouse (SWGH) system. Power consumption and water productivity of the SWGH are predicted using the proposed RVFL-AEO model. The statistical analyses using different statistical criteria such as root mean square error, mean absolute error, mean relative error, efficiency coefficient, coefficient of determination, overall index, and coefficient of residual mass are also carried out to examine the efficiency of the proposed neural network. The statistical tools obtained a perfect match between the experimental and the proposed model results. The performance of the RVFL-AEO model is compared with that of the conventional RVFL model. RVFL-AEO showed a better performance compared with RVFL; which indicates the role of AEO in obtaining the optimal RVFL parameters that enhances the accuracy of the model.