Techno-Economic Analysis of a 12-kW Photovoltaic System Using an Efficient Multiple Linear Regression Model Prediction

Abstract

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.

Confirmed Malaria Cases in Children under Five Years: The Influence of Suspected Cases, Tested Cases, and Climatic Conditions

“…Te plots show that there exists a linear relationship between each independent variable and the dependent variable; hence, the application of the multiple linear regression model is justifed [45,46]. Te correlation plots also show signifcant high positive correlation between suspected cases and tested cases which indicate the presence of collinearity between two independent variables if both are considered in the model and could lead to redundancy of one of them.…”

“…Te validity of predictions from the ftted model abovementioned is ensured provided that the assumptions of linearity, normality, and homoscedastic (constant) are satisfed by examining the various residual plots [45,46]. From the abovementioned, we have the following equation:…”

Using machine learning prediction to design an optimized renewable energy system for a remote area in Italy

“…The required power converters are a DC-DC converter to charge the battery and an inverter to feed the customers [17], [18]. Additionally, it is vital to forecast the area's potential energy using machine learning algorithms and data analysis before investing any money in a renewable system [19]- [21]. This paper used a linear regression model to forecast both solar and wind energy in the considered remote area.…”

Optimizing Solar Energy Harvesting: Supervised Machine Learning-Driven Peak Power Point Tracking for Diverse Weather Conditions

“…GA comprise functions like crossover and mutation, which are computational complex and like CSA this algorithm is also parameter sensitive. The MLA [15], [19], [20], [24], [30], [33] is used by the researchers. The researcher proposed a multiple linear regression model for forecasting of power under varying weather [24].…”

“…The MLA [15], [19], [20], [24], [30], [33] is used by the researchers. The researcher proposed a multiple linear regression model for forecasting of power under varying weather [24]. The model predict the power with less than 6% error as an actual power.…”