KVO997: ENHANCING PHOTOVOLTAIC POWER PREDICTION ACCURACY USING REAL-DATA-TRAINED ARTIFICIAL NEURAL NETWORK (ANN)

Cempaka Amalin Binti Mahadzir Universiti Tun Hussein Onn Malaysia

I3DC24 | Tertiary (Online)

CR: 0.1200 | 3 Likes | 25 Views | 152 times | LS: 155.4
Like it? | Support them now!

One of the cleanest and most renewable energy sources with the most promise to solve the world's energy problems is photovoltaic (PV) energy. Nonetheless, a significant disadvantage of the PV system is that the dependability of the PV panels' ability to generate electricity is incompatible and heavily dependent on variations in weather. Predicting the ideal power output of PV system is therefore crucial. Regarding this, the aim of this research endeavour is to analyse the potential of utilising Artificial Neural Networks (ANN) and Graphical User Interfaces (GUI) to predict power output based on actual data acquired by Blynk Apps. While a GUI system can improve the prediction process, an ANN setup can be implemented for predicting solar power output.