Short Term Forecast of Solar Photo Voltaic Power

Research Supervisor
Journal Title
Journal Title
Journal ISSN
Volume Title
The rapid growth of solar photovoltaic technology is providing great interest in substituting the non-renewable energy demand. Solar power forecasting can avoid many of the balancing issues. Forecasting power demand plays an essential role in the electric industry, as it provides the basis for making decisions in power system planning and operation. The method of predicting the generated power from solar panel merely relies on historical solar power data. The method requires no specific equipment, sensor data, or weather predictions. In order to build solar pv technology model, Extreme Gradient Boosting, Long Shorth Term Memory model and Autoregressive integrated moving average model has been introduced. These models provide reliable information that will help to operate efficient photovoltaic power plants in the future. In this project, software applications are built for prediction of Forecasting Solar Energy prototype using Python (Machine Learning). Our work does not need any user interface (UI) & but it includes formulating optimized algorithms required for its operation. We completed our whole software part on Google Colab. We used i) ARIMA model for measuring our time period, ii) an approved LSTM enhanced forget-gate network to predict solar power generation, iii) XGBoost for accurate prediction and open-source implement. Our main task was to took some data of energy power and after analyzing it the machine will predict how much energy we need for a least time in the next day.
Department Name
Electrical and Computer Engineering
North South University
Printed Thesis