Differential Evolution with Concurrent Fitness Based Local Search

This paper proposes a novel implementation of memetic structure for continuous optimization problems. The proposed algorithm, namely Differential Evolution with Concurrent Fitness Based Local Search (DEcfbLS), enhances the DE performance by including a local search concurrently applied on multiple individuals of the population. The selection of the individuals undergoing local search is based on a fitness-based adaptive rule. The most promising individuals are rewarded with a local search operator that moves along the axes and complements the normal search moves of DE structure. The application of local search is performed with a shallow termination rule. This design has been performed in order to overcome the limitations within the search logic on the original DE algorithm. The proposed algorithm has been tested on various problems in multiple dimensions. Numerical results show that the proposed algorithm is promising candidate to take part to competition on Real-Parameter Single Objective Optimization at CEC-2013. A comparison against modern meta-heuristics confirms that the proposed algorithm robustly displays a good performance on the testbed under consideration.