Differential Evolution Made Faster And More Robust

In this paper, an improved version of the differential evolution (DE) based on the orthogonal design (ODE) is presented to make the DE faster and more robust. The ODE combines the conventional DE (CDE), which is simple and efficient, with the orthogonal design, which can exploit the optimum offspring. The ODE has some new features. (1) It uses a robust crossover based on orthogonal design and an optimal offspring is generated with the statistical optimal method. (2) Decision variable fraction strategy is applied to decrease the number of the orthogonal design combinations and make the algorithm converge faster. (3) The ODE simplifies the scaling factor F of the CDE, which can reduce the parameters of the algorithm and make it easy to use for engineers. We execute the proposed algorithm to solve twelve benchmark functions with low or high dimensions and a large number of local minima. Simulations indicate that the ODE is able to find the near-optimal solution in all cases. Compared with some state-of-the-art evolutionary algorithms, the performance of the ODE outperforms other evolutionary algorithms in terms of the quality of the final solution and the stability; and its computational cost (measured by the average number of fitness function evaluations) is lower than the cost required by the other techniques compared.