Non-equidistant grey prediction evolution algorithm: A mathematical model-based meta-heuristic technique

A grey predictive evolutionary algorithm, which is attracting more and more attention, regards the population series of evolutionary algorithms as an equidistant time series. The population evolution is essentially regarded as a process in which the function values have variable-speed decrease with the increase of the number of iterations (for minimization problems). Therefore, a fitness-driven evolutionary population sequence with the property of variable-speed evolution should be more appropriately modelled as a non-equidistant time series. A novel meta-heuristic optimization algorithm, non-equidistant grey prediction evolution algorithm is proposed in this paper. The proposed algorithm is identified by its reproduction operator which is developed by the following two steps. Firstly, a non-equidistant grey model (NeGM (1,1)) based on the average fitness value of each generation population to preserve the non-equidistant nature is modelled. Secondly, the interval in the fitting stage of the NeGM (1,1) is defined as an increasing time interval. The performance of the proposed algorithm is evaluated on CEC2019 and CEC2020 benchmark functions. Experimental results show that the proposed algorithm is superior to other more complex and notable approaches, in terms of solving accuracy as well as the rate of convergence. The Matlab code of this paper is availabled on https://github.com/Zhongbo-Hu/Prediction-Evolutionary-Algorithm-HOMEPAGE.