Forecasting Photovoltaic Output Power Based on Environmental Parameters Using Artificial Neural Network Methods

Abstract

Photovoltaics are systems that can convert sunlight into electrical energy. However, photovoltaic efficiency tends to be low, and its performance is affected by several environmental parameters such as dust, wind speed, humidity, temperature, and other external factors. Because there are many factors that can affect the power generated, we need a power output prediction system that can help in planning and managing as well as increasing the efficiency of photovoltaic systems. In this research, a system is designed that can predict the photovoltaic output power in the short term using the artificial neural network method or what is often called an artificial neural network. Predictions are made based on the effects of several environmental parameters such as wind speed, dust, humidity, and temperature on a 10 Wp photovoltaic system. Performance data for 7 days is used as a dataset and then processed using ANN with 1 input layer, 3 hidden layers, and 1 output layer, and 3 sample epochs (10, 100, and 1000). The results of the study can predict the output of photovoltaic power for the next 4 days with an error value of Mean Square Error (MSE) of 0.0010, Mean Absolute Error (MAE) of 0.0155, Root Mean Square Error (RMSE) of 0.0229 with an increase in power reaching 0.5 to 1 watt.