Best Practices on Metamodel-Based Photovoltaic Monitoring System with Prediction Method for Photovoltaic Power Generation

Abstract

HS Solar Energy Company Inc. in Sejong city, Korea, has a big problem on how to monitor heterogeneous inverters with different protocols. Still a current photovoltaic power plant with different inverters, it has attracted significant attention to its experience of difficulties in monitoring integrated power generation. To solve this problem for the company, we adapt a metamodel mechanism to easily manage and integrate heterogeneous data into a metamodel-based data format. The existing metamodel-based photovoltaic monitoring system (M-PVMS) of the HS solar energy company also needs to simply predict the photovoltaic power generation in a day for small farm owners in the countryside. Therefore, we propose a method for predicting the power generation of M-PVMS panels using the gated recurrent unit (GRU) algorithm, which supports real-time learning to predict the photovoltaic system behavior that rapidly accumulates data in real time. As a result, we can predict the power generation for small farm owners with a probability of 96.353%.