RCOA: A hybrid bio-inspired metaheuristic based on Rangoon Creeper growth dynamics for sustainable supply chain optimization in complex nonlinear systems

Efficient and sustainable supply chain optimization in complex nonlinear environments remains a challenging problem due to uncertainty, dynamic constraints, and multi-objective decision requirements. This study proposes a novel Rangoon Creeper Optimization Algorithm (RCOA), a bio-inspired metaheuristic modeled on the adaptive growth behavior of Quisqualis indica . The proposed algorithm integrates tendril-based exploration, twining-based exploitation, and adaptive branching mechanisms to effectively balance global and local search. A multi-objective supply chain model is formulated to minimize total operational cost, delivery time, and environmental impact under capacity and flow constraints. The proposed framework is further enhanced by incorporating a blockchain-based traceability layer for secure and transparent transaction management. Experimental evaluation is conducted using both synthetic datasets and standard benchmark optimization functions across multiple problem sizes. The performance of RCOA is compared with Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO). Results demonstrate that RCOA achieves up to 15% reduction in operational cost, 20% reduction in delivery time, and significantly improved convergence speed and stability. Statistical analysis confirms the robustness and consistency of the proposed method. The findings highlight the potential of RCOA as a scalable and intelligent optimization framework for real-world applications in sustainable supply chain management and complex decision-making systems.