Life cycle assessment and forecasting for 30kW solar power plant using machine learning algorithms

•The objective of this paper is to investigate different machine learning algorithms can accurately anticipate solar power for the upcoming hour and hourly days under different weather data and seasonal effect.•The Naïve Bayes Algorithm, Multilayer Perceptron Theorem (MLP), and Long Short-Term Memory networks (LSTM) are the machine learning algorithms investigated for a 30 kW solar PV plant.•The life cycle assessment and payback period for a 30 kW solar PV power plant is also determined. Highly competitiveness of solar power plants in the energy market requires addressing the active research problem of solar energy forecasting. To make precise forecasts, however, historical meteorological, production, or irradiance data is insufficient. As the conservation of these Renewable Energy Sources (RES) is that much essential, the use of Photovoltaic (PV) panels have subsequently increased. The output of these PV panels completely depends on the climate. As the PV panels convert the solar energy to electrical energy, therefore, it produces the most when there is enough sunlight throughout the summer and the least when there is rain. Accurate forecasting of energy generation from solar power plants is crucial in terms of economics due to this uncertainty in the output in different seasons and the change in meteorological conditions. The objective of this paper is to investigate machine learning algorithms can accurately anticipate solar power for the upcoming hour and hourly days in advance. The Naïve Bayes Algorithm, Multilayer Perceptron Theorem (MLP), and Long Short-Term Memory networks (LSTM) are the machine learning algorithms investigated. Both historical weather data and generation data are used in the study. This study also includes the payback period (PB) and life cycle assessment calculation of the roof top solar power plant located in Bhubaneswar India.