Solar cell is one of the important renewable energy resources, and it is considered a promising source for energy challenges in the future. The identification of solar cell model parameters is very important due to the control and the simulation of PV systems. In this paper, an enhanced teaching–learning-based optimization (ETLBO) algorithm is proposed and applied to estimate the photovoltaic cells parameter. The ETLBO is proposed to improve the performance of conventional TLBO and reduce its search space by adjusting the parameters which control the explorative and exploitative phases to achieve the suitable balancing. The proposed algorithm is validated using real dataset of photovoltaic single-diode and double-diode models. In addition, the proposed algorithm is tested on the dataset of two real PV panels (polycrystalline and monocrystalline). The results obtained by the proposed algorithm are compared with those obtained by other well-known optimization algorithms. All results prove the effectiveness and superiority of proposed algorithm compared with other optimization techniques.