Cost Effective Energy Saving Optimisation Technique Using Hybridised Augmented Grey Wolf Optimiser and Ant Colony Models in Industrial Buildings. A Case Study of CWAY Integrated Limited, Abuja

Abstract

This research develops and evaluates a hybridised optimisation approach combining Augmented Grey Wolf Optimiser (AGWO) and Ant Colony Optimisation (ACO) algorithms for building energy management. The study addresses the pressing need for energy efficiency in buildings, which account for approximately 40% of global energy consumption. Using a case study of CWAY Integrated Limited in Abuja, Nigeria, the research compared standalone AGWO, standalone ACO, Sequential Hybrid, and Average Hybrid models across multiple performance metrics. The ACO algorithm demonstrated superior performance with a 22.9% reduction in daily energy costs (from ₦632,250 to ₦487,350), followed by AGWO with a 21.0% reduction. Contrary to expectations, the Sequential Hybrid approach underperformed both standalone algorithms with only a 13.1% cost reduction, while the Average Hybrid achieved a 19.0% reduction. Statistical analysis confirmed significant performance differences between optimisation approaches, with the Kruskal-Wallis test yielding a p-value of 2.83×10⁻⁸⁶. Component-wise analysis revealed that all optimisation approaches prioritised reductions in energy-intensive components while maintaining stable operation for components with stricter operational constraints. The research demonstrates that metaheuristic optimisation techniques can achieve significant energy savings in building operations while maintaining operational requirements, with important implications for sustainable building management practices.