Abstract
Online optimization applications require fast convergence without sacrificing accuracy. Although the gray wolf optimization (GWO) algorithm is showing good convergence performance, it still needs further improvement to achieve these requirements. Optimal determination of the GWO control parameters can substantially improve the converge performance. All studies in the literature introduced efforts in tuning these parameters on try-and-error bases which may not satisfy the requirements of the online applications. For this reason, a novel nested improved GWO (NEST-IGWO) is used to determine the optimal control parameters for the IGWO. This novel strategy substantially improved the convergence time and accuracy, especially with online control systems. This strategy is having two nested IGWO loops. The internal IGWO loop includes the target function needed to be optimized. Meanwhile, the external loop is used to optimally determine the control parameters of the internal one. The objective function of the external loop is the failure rate and convergence time of the internal one. The results obtained from the NEST-IGWO are compared to 10 existing optimization algorithms for 10 different benchmark functions. Moreover, these optimization algorithms were applied to determine the parameters of the PV-cell model as a real-world application. The results showed that NEST-IGWO outperformed the other 10 optimization algorithms for all benchmark functions understudy and the estimations of the PV-cell parameters in terms of failure rate and convergence time. With the use of the NEST-IGWO, the convergence time is reduced by 90% of the average convergence time for all other algorithms. Moreover, the failure rate is reduced to 0% which is not the case for other algorithms understudy. These outstanding results prove the superiority of the NEST-IGWO compared to the other algorithms, and it opens a new venue for determining optimal control parameters for all optimization algorithms.