Abstract
Recently, meta-heuristic optimization algorithms have enhanced resource efficiency, facilitated informed decision-making, and addressed complex problems involving multiple variables and constraints in engineering and science fields. However, numerous handicaps are reported on the performance of a quite number of these optimizers, such as local solution trapping, slow convergence and the requirements for elevated storage and computation capability. This article proposes a novel, simple, and elaborate remedy for the reported deficiencies of meta-heuristic optimizers. This deficiency is accomplished by proposing a hybrid optimizer composed of an ambiguous optimizer and Artificial Intelligence (AI). The performance of the proposed technique is evaluated using four different meta-heuristic optimizers: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Teaching-Learning-Based Optimization (TLBO), and Artificial Gorilla Troops Optimization (AGTO). These optimizers range from the mature to the recently evolved. These meta-heuristic optimizers validate the proposed solver and confirm its applicability to any meta-heuristic optimization algorithm. Economic Dispatch (ED) of the IEEE 30-bus system is utilized to evaluate the performance of the proposed solver. The comprehensive results demonstrate the superiority, reliability, and adequacy of the proposed technique. It consistently converges to the global optimum solution, achieving the minimum energy cost of the system under concern while requiring the fewest iterations and minimal computational requirements.