ASSOCIATION RULE ALGORITHM FOR WEATHER FACTORS ESTIMATION USING ON-GRID SOLAR PV POWER SYSTEM

Many stations are established worldwide to measure the weather factors such as temperature, humidity, wind speed, and cloud cover. In this paper, A developed model using association rule mining algorithm is utilized to predict weather factors from real power photovoltaic PV system on-grid. This model is tested on Tafila Technical university PV system data. The developed model contributes successfully as a virtual weather station to forecast the weather in Tafila-Jordan region. The extracted rules of the model are examined by a weather forecasting expert in order to validate the developed system. The results show high confidence and accuracy. The predicted weather factors from PV power values matched approximately 97% of the results given by the experts.