Abstract
This article proposes a compact algorithm for optimisation in noisy environments. This algorithm has a compact structure and employs differential evolution search logic. Since it is a compact algorithm, it does not store a population of solutions but a probabilistic representation of the population. This kind of algorithmic structure can be implemented in those real-world problems characterized by memory limitations. The degree of randomization contained in the compact structure allows a robust behaviour in the presence of noise. In addition the proposed algorithm employs the noise analysis survivor selection scheme. This scheme performs an analysis of the noise and automatically performs a re-sampling of the solutions in order to ensure both reliable pairwise comparisons and a minimal cost in terms of fitness evaluations. The noise analysis component can be reliably used in noise environments affected by Gaussian noise which allow an a priori analysis of the noise features. This situation is typical of problems where the fitness is computed by means of measurement devices. An extensive comparative analysis including four different noise levels has been included. Numerical results show that the proposed algorithm displays a very good performance since it regularly succeeds at handling diverse fitness landscapes characterized by diverse noise amplitudes.