Hybrid Coyote Optimization with Differential Evolution and its Application to the Estimation of Solar Photovoltaic Cell Parameters

Abstract In order to obtain a Coyote optimization algorithm (COA) is with universal applicability, this paper proposes a novel hybrid algorithm based on COA and Deferential Evolution (DE), named DECOA. Firstly, Global optimum guidance growth scenario of alpha coyotes is introduced into the growth procedure of the alpha coyote of each group, which enables the scenario to approach the global optimum result faster. Secondly, a Gaussian global growth operator is randomly adopted in the growth procedure of ordinary coyotes to make better the global search capacity while preserving the vigorous local search capacity. Thirdly, in order to further improve the social adaptability of coyotes after they grow up, differential expulsion and admission strategy is integrated. Finally, the numbers of the groups are dynamically modified to balance exploitation and exploration. A large number of tests on the benchmark functions from CEC-2017 and CEC-2013 test sets verify the proposed strategy. Especially, compared to many state-of-the-art algorithms, the proposed strategy ranks first 15 times among 29 benchmark functions of CEC-2017 and the average running speed has reached 2.29s. It is extremely important to obtain the PV cell parameters effectively, because the required data to model PV cells will be not provided by the manufacturers. Hence, DECOA is further applied to the scene of parameter estimation of photovoltaic solar cells and modules and the results still indicate that it surpasses the other advanced comparison scenarios.