The use of solar energy is more popular in recent years since the abundant availability and negligible pollution compared to conventional sources of energy. But the availability of solar energy varies according to locations, so it is better to know the amount of power that can be generated by the installed solar plant. This helps to supply the power obtained by the solar panel to distribution grids in case of an overload condition. Different methods are available to estimate the power output of the solar panel. In this paper, the estimation of the output power of a Solar Photovoltaic System is done. A new thermal model of a solar PV system has been used for obtaining the state space representation of the system. The solar PV panel power output estimation is done by using different linear and non-linear methods such as Hammerstein-winner model, Transfer function model, and Non-linear ARX model have been estimated and compared with the Kalman filter. A comparative study of different estimation methods is presented in this paper.