Impact of Distinct Weather Parameters on Simultaneous Prediction of Solar Power and Load Demand using LSTM Model

Abstract

Forecasting of solar energy and load demand plays very vital role in energy management system. Forecasting of load and solar power depend on various factors like time horizon, weather conditions etc. of region. So to have their accurate prediction, it is necessary to consider as many factors as possible that affect the uncertainties of solar generation and load demand. This paper has considered different weather parameters like air density, radiance, temperature, precipitation, cloud cover and irradiance to predict solar based power generation and load demand simultaneously using long short term memory (LSTM) models. The root mean square error and mean absolute percentage error metrics are used to analyze the performance of the above framed structure.