Renewable energy sources are expected to replace traditional energy sources such as oil and gas in the future. It goes without saying that solar energy has been demonstrated to be a key source of green energy. Solar energy is used because it is abundant, pollution-free, and easily available. However, the power utility market requires highly exact solar energy forecasts. These challenges need the creation of a device that can precisely predict solar energy output via processing the location's weather data, which is accomplished through the use of machine learning and multiple linear regression (MLR). Some elements, such as the number of cloudy days, humidity, temperature, wind condition, and precipitation, should be addressed while simulating solar power output. In this paper, a 12-kW photovoltaic (PV) system on the rooftop of a house in Isfahan was studied using the System Advisor Model (SAM). The most significant research contribution of the proposed paper is to predict the output power of a solar system with the lowest possible error. According to the simulation results, by using the MLR model, the predicted power has an error of 6 % with the actual power, which is a very good estimation. In addition, this system meets each household's energy needs plus an additional 8430 kWh per year, resulting in being paid by utility companies, a fewer number of outages, and lower air pollution levels.