PLTS is a power plant that is highly dependent on the intensity of solar irradiation, but its energy production is unstable because it is greatly influenced by weather conditions. Therefore, a solar irradiation projection is needed to assist in forecasting solar irradiation using RStudio. In this projection process, the Seasonal Autoregressive Integrated Moving Average (SARIMA) method and Long Short-Term Memory (LSTM) are used. This projection will result in solar irradiation forecasting data for 5 years (60 months) from January to December in the years 2024 to 2028. SARIMA with the Arima (1,0,0) (0,1,1)12 modeling yields an RSME value of 0.04524378, MAE of 0.03336635, and MAPE of 0.5554528%. The forecasting results of the hybrid SARIMA (SARIMA+LSTM) show an RSME of 1.998118, MAE of 1.549476, and MAPE of 0.3811224%. From the comparison of SARIMA and hybrid SARIMA (SARIMA+LSTM), the hybrid SARIMA is better used for forecasting solar irradiation because it has the smallest percentage of error. The hybrid SARIMA can also capture nonlinear data that is not processed in SARIMA, and the graph from the hybrid SARIMA tends to follow the pattern of the data, resulting in a very small distance between the raw data and the forecasting results.