Abstract: The utilization of renewable energy to lessen climate change and global warming has become an expanding pattern. To further develop the prediction capacity of renewable energy, different prediction techniques have been created. Predicting the full load electrical power output of a base burden power plant is significant to amplify the benefit from the accessible megawatt-hours. This paper looks at and analyzes some machine learning relapse strategies to foster a prescient model, which can foresee the full hourly burden electrical power output of a combined cycle power plant. The base burden activity of a power plant is affected by four primary boundaries, which are utilized as info variables in the dataset, like ambient temperature, atmospheric pressure, relative humidity, and exhaust steam pressure. These boundaries influence electrical power output, which is considered the objective variable. The dataset, which comprises this information and target variables, was gathered over six years. In light of these variables, the best subset of the dataset is explored among all component subsets in the examinations.