This paper presents a new metamodel-assisted metaheuristic algorithm for optimisation problems involving computationally expensive simulations. The algorithm, called Global Probing Search, is a population-based algorithm designed for global optimisation. The main idea of the algorithm is to introduce a probing phase in the creating of the new generation of the population. In this probing phase, a large number of candidate solutions are generated and a computationally cheap metamodel function is used for choosing the most promising candidates to transfer to the next generation. This approach could significantly enhance the efficiency of the optimisation process by avoiding wasting valuable evaluation time on solutions that are likely to be inferior. During the optimisation, the accuracy of the metamodel is constantly improved through on-line updating. The proposed algorithm is implemented on a real-world optimisation problem and initial results indicate that the algorithm show good performance in comparison with a standard Genetic Algorithm and an existing metamodel-assisted metaheuristic.