Accurate parameter estimation of photovoltaic (PV) cells is crucial for establishing a reliable cell model. Based on this, a series of studies on PV cells can be conducted more effectively to improve power output; an accurate model is also crucial for the operation and control of PV systems. However, due to the high nonlinearity of the cell and insufficient measured current and voltage data, traditional PV parameter identification methods are difficult to solve this problem. This article proposes a parameter identification method for PV cell models based on the radial basis function (RBF). Firstly, RBF is used to de-noise and predict the data to solve the current problems in the parameter identification field of noise data and insufficient data. Then, eight prominent meta-heuristic algorithms (MhAs) are used to identify the single-diode model (SDM), double-diode model (DDM), and three-diode model (TDM) parameters of PV cells. By comparing the identification accuracy of the three models in two datasets in detail, the final results show that this method can effectively achieve parameter extraction, with advantages such as high extraction accuracy and stability, greatly improving the accuracy and reliability of parameter identification. Especially in the TDM, the I-V data and P-V data obtained from the PV model established through the identified parameters have very high fitting accuracy with the measured I-V and P-V data, reaching 99.58% and 99.65%, respectively. The research can effectively solve the low accuracy problem caused by insufficient data and noise data in the traditional method of identifying PV cells and can greatly improve the accuracy of PV cell modeling. It is of great significance for the operation and control of PV systems.