Developments and Design of Differential Evolution Algorithm for Non-linear/Non-convex Engineering Optimization

Nowadays, the differential evolution (DE) achieved noticeable progress and solved a wide range of non-linear/non-convex engineering optimization issues. As a strong optimizer, DE has many advantages like simple structure, strong exploitation ability and considerable convergence speed. However, DE also suffers from low diversification, poor exploration ability and stagnation. After significant reviewing and to avoid aforesaid gaps, this paper reports a modified DE (mDE) for solving non-linear/non-convex optimization problems, especially non-convex economic dispatch (ED). It adopted novel mutation strategy with new control parameters using concept of particle swarm optimization (PSO), to enhance exploration and exploitation activities more profusely and increase the global search capability. Also, a new crossover rate is employed in mDE, to attain higher convergence accuracy and quality optimal solutions. Finally, a novel selection strategy is introduced in mDE, to facilitate information sharing as well as for escaping local minima and keeps evolving. To validate the mDE performance, IEEE CEC2006 non-linear constrained benchmark suites are solved. Furthermore, its practicality, efficacy and excellence are further demonstrated in six complex non-linear engineering optimization issues and six cases (3, 6, 13, 15, 40 and 140-unit system) of non-convex ED problems. Besides, the mDE results are compared with other peer meta-heuristic methods. Comparison results analysis validates the competitive presentation of the developed mDE.