Building energy consumption prediction using multilayer perceptron neural network-assisted models; comparison of different optimization algorithms

Building energy prediction has gained significant attention as a thriving research field owing to its immense potential in enhancing energy efficiency within building energy management systems. Therefore, the objective of this study is to predict the values of cooling and heating loads by utilizing the multilayer perceptron neural network for predictive purposes. In this context, a multilayer perceptron neural network is chosen as the core framework for addressing the problem at hand. Subsequently, employing a hybridization approach, multilayer perceptron is combined with eight meta-heuristic algorithms to effectively tune and optimize the hyperparameters of the multilayer perceptron model. Statistical analysis is conducted to examine the performance of each hybrid model. The findings indicate that MLP-PSOGWO exhibits the best performance, demonstrating the highest levels of accuracy, authenticity, and efficiency. According to the obtained results, it is reported that the MLP-PSOGWO model achieves the highest total R2 values of 0.966 for the cooling load and 0.998 for the heating load. These values surpass those of all other models, indicating that the MLP-PSOGWO model demonstrates the best performance among the hybrid models. Importantly, the results obtained underscore the overall effectiveness of the selected optimizers in delivering accurate outcomes.