Avoiding stagnation at local optimum values is one of the greatest challenges faced by computational intelligence techniques when solving nonconvex optimization problems. The transition between global and local search may not be effective and can compromise the performance of optimization algorithms. This work presents a novel manner to update the exploration coefficient of the meta-heuristic known as grey wolf optimizer (GWO), by replacing the linear update of the exploration coefficient by a triangular-shaped function, enabling the algorithm to escape from local optima. In order to validate the proposed grey wolf optimizer (PGWO) methodology, its performance is compared to the original version of GWO and its chaotic version, as well as to the well-known genetic algorithm, bat algorithm and particle swarm optimization techniques, in solving 10 nonconvex benchmark functions. Also, in order to verify the proposed methodology’s ability in solving a more realistic engineering problem, the authors implemented the PGWO to solve the wind farm layout optimization (WFLO) problem, which is a large-sized optimization problem, of combinatorial nature and nonconvex solution region. The results indicate that the PGWO improved the performance of the original GWO, as well as all investigated methodologies for the benchmark functions optimization and for the WFLO problem.