Proposing a novel predictive technique using M5Rules-PSO model estimating cooling load in energy-efficient building system

In this study, we employed the most suitable artificial intelligence systems and optimized it with a novel evolutionary algorithm called particle swarm optimization (PSO) for the problem of cooling load (C-L) in energy-efficient building (EEB) system. Then, the mentioned methods are utilised to identify a relationship between the input and output parameters of the EEB system. The amount of C-L was taken as the essential output of the EEB system, while the input parameters were channel length, channel depth, channel width, and air mass flow rate. The predicted results for data sets from each of the abovementioned models were evaluated according to several known statistical indices such as correlation coefficient (R-2), mean absolute error (MAE), root mean squared error (RMSE), relative absolute error (RAE), and root relative squared error (RRSE) as well as novel ranking systems of colour intensity rating and total ranking method. The M5Rules has been proposed as the best predictive network in this study. The results of the M5Rules network indicated the R-2, MAE, RMSE, RAE, and RRSE for the training and testing data sets were 0.9982, 0.0426, 0.0653, 6.2344, and 6.0298 and 0.7626, 0.9903, 0.9593, and 0.9981, respectively. According to R-2, RMSE, and VAF, values of 0.99983, 0.0066, and 99.98 and 0.9982, 0.065, and 84.5 were obtained for testing data set and values of proposed PSO-M5Rules prediction network models, respectively. This indicates higher reliability of the introduced PSO-M5Rules model in approximating C-L of an EEB system.