Examination of Possibility of Improving Accuracy on Predicting Photovoltaic Power Generation in Snowy Areas Using Panel Images

Abstract

After the sequential end of feed-in tariff (FIT), the electricity generated by photovoltaic (PV) power generation system must be consumed by consumers themselves. Since PV power generation volume is easily affected by weather conditions, it is often used in combination with a power storage device to provide a stable power supply using PV power generation system. However, in order to efficiently control the power storage device according to the amount of power supplied by PV power generation system, it is necessary to accurately predict PV power generation volume. In this research, we will propose a method for predicting PV power generation volume by grasping the snow cover condition of the panel based on the panel image taken by the surveillance camera. We will compare and evaluate the prediction of PV power generation using the snow cover predicted from the panel image with related research and confirm the effectiveness of the proposed method.