Solar power is one of the most popular green energy. Recently, a large number of Photovoltaics(PV) are installed worldwide. However, the main challenge of PVs is that the produced electricity is often variable and intermittent. The fluctuation of the supply makes the energy expensive and prevent it form prevalence. Due to the unpredictable nature, the grid operators usually need to adopt a more conservative strategy and reserve enough power. If the reserved power is not used, it is a waste. If the reserved power is not enough, a black-out would happen. Therefore, the ability to make short-term PV production prediction is necessary for grid operators. In this work, we aim at predicting the solar irradiance in order to let the PV operators allocate other energy supplies if necessary. The systems would aim at automatically analyze the relationship of the sun and the clouds. If a cloud is predicted to block the sun, the grid operator could forecast the drop of solar irradiance and appropriate energy allocation can be made.