Photovoltaic cell models involve nonlinear and complex parameters, and traditional identification methods often suffer from slow convergence and local optima issues, limiting their efficiency. Metaheuristic algorithms have been developed to enhance the accuracy and efficiency of parameter identification. This paper proposes a coati improved snow ablation optimization (CSAO) incorporating Weibull distribution and elite retention. First, a random probability mechanism combines the coati optimization algorithm with the basic snow ablation optimization, enhancing its global search capability. Second, a search mechanism based on Weibull distribution is incorporated to broaden the search range during local exploitation, helping to avoid falling into local optima. Finally, an elite retention strategy is added to accelerate convergence speed. The CSAO algorithm was evaluated using the CEC2017 benchmark function set. The CSAO algorithm was used for parameter identification of three photovoltaic models (single-diode, double-diode, and triple-diode) and three types of photovoltaic modules named Photowatt-PWP201, STM6-40/36, and STP6-120/36 respectively. Experimental results demonstrate that, compared to other algorithms, CSAO provides more accurate and stable parameter identification for photovoltaic cells and modules, along with faster convergence.