Enhancing sustainable urban design using machine learning: comparative analysis of seven metaheuristic algorithms in energy-efficient digital architecture

Metaheuristics optimization algorithms used in this research include PSO, ACO, GA, and SA and represent effective approaches toward reaching an optimal or near-optimal solution for decision variables with an intention to improve energy efficiency, increasing indoor comfort whilst reducing the carbon footprint of building operations. These algorithms will be applied across different sizes of a synthesized data pool prepared with important features like window-to-wall ratio, efficiency in HVAC systems, renewable systems integration, among others. PSO demonstrated the best scenario in both cases with an optimum convergence rate of 24.1%; ACO produced almost the same best result as mentioned with high rates of reductions in carbon footprints. These had their best energy-savings while convergence in GA and SA was extremely slow with energy efficiencies that turned out to be pretty low. This could enable real proposals to be made to architects, urban planners, and policy thinkers, allowing them to turn such ideal cases into viable realities within sustainable development initiatives.