Optimized Low‐Emission Combustion in Domestic Biomass Boilers: A Comparative Study Using Artificial Bee Colony Algorithm for Enhanced Efficiency and Reduced Pollutant Emissions

ABSTRACT Biomass boilers are widely used for sustainable heating, but combustion inefficiencies lead to significant emissions of CO, NO x , and particulate matter, affecting both performance and air quality. Traditional control strategies like Fuzzy Logic Control (FLC) often rely on fixed rule sets, limiting adaptability in dynamic combustion environments. This study aims to optimize air‐fuel balancing in a 10 kW domestic biomass boiler using the Artificial Bee Colony (ABC) algorithm, with the dual objective of minimizing harmful emissions and maximizing thermal efficiency. Combustion data was collected under varying operating conditions, and an optimization model was developed using ABC. A 50‐iteration optimization process was executed, and the results were benchmarked against FLC. ABC achieved a 28% reduction in CO, 21% in NO x , and 30% in particulate matter, with a 3.8% improvement in thermal efficiency. It also demonstrated a 54% enhancement in fitness score and faster convergence than FLC. The novelty of this study lies in the first‐ever application of the ABC algorithm for real‐time biomass combustion optimization. Unlike FLC, ABC dynamically explores optimal solutions, offering a more adaptable, computationally light, and globally optimized control mechanism. This establishes a new direction in intelligent emission control, advancing cleaner and more efficient biomass energy systems.