Synthesizing Multi-Layer Perceptron Network with Ant Lion Biogeography-Based Dragonfly Algorithm Evolutionary Strategy Invasive Weed and League Champion Optimization Hybrid Algorithms in Predicting Heating Load in Residential Buildings

The significance of accurate heating load (HL) approximation is the primary motivation this research to distinguish most efficient predictive model among several neural-metaheuristic models. proposed models are formulated through synthesizing a multi-layer perceptron network (MLP) with ant lion optimization (ALO), biogeography-based (BBO), dragonfly algorithm (DA), evolutionary strategy (ES), invasive weed (IWO), and league champion (LCA) hybrid algorithms. Each ensemble optimized in terms operating population. Accordingly, ALO-MLP, BBO-MLP, DA-MLP, ES-MLP, IWO-MLP, LCA-MLP presented their best performance for population sizes 350, 400, 200, 500, 50, 300, respectively. comparison was carried out by implementing ranking system. Based on obtained overall scores (OSs), BBO (OS = 36) featured as capable technique, followed ALO 27) ES 20). Due these algorithms, corresponding MLPs can be promising substitutes traditional methods used HL analysis.