A New Method of Detecting Hot Spots in PV Generation System Utilizing AI

Abstract

Abstract Photovoltaic (PV) Generation system is one of the easiest green energy systems to generate small amounts of energy as in houses or for large amounts as in fields. Although PV generation system does not burn fuel for power generation, it does still faces some problems regarding heat. One of these problems are called Hotspots. Hotspot is an increase of the cell`s heat in certain conditions and positions. In some cases, the heat can even start a fire. In this study, we propose a new method to detect this hotspot phenomenon in an early stage. The proposed method utilizes Artificial Intelligence (AI) as the main detection system. In fact, we were able to detect the hotspot with an accuracy of 82.25% using only two parameters, string current and string voltage. This system is a secondary system to be used with the main control system. The output will be a flag sent to the main controlling system. Making this system a secondary one, makes it easier to apply in already built PV fields. In near future, the detection of other deficiencies is going to be a major task for this system.