Estimating Heating Load in Residential Buildings Using Multi-Verse Optimizer, Self-Organizing Self-Adaptive, and Vortex Search Neural-Evolutionary Techniques

Using ANN algorithms to address optimization problems has substantially benefited recent research. This study assessed the heating load (HL) of residential buildings’ heating, ventilating, and air conditioning (HVAC) systems. Multi-layer perceptron (MLP) neural network is utilized in association with MVO (multi-verse optimizer), VSA (vortex search algorithm), SOSA (self-organizing self-adaptive) solve computational challenges compounded by model’s complexity. In a dataset that includes independent factors like overall height glazing area, orientation, wall compactness, distribution HL goal factor. It was revealed metaheuristic ensembles based on MVOMLP VSAMLP metaheuristics had solid ability recognize non-linear relationships between these variables. terms performance, MVO-MLP model considered superior VSA-MLP SOSA-MLP models.