Modeling and Forecasting Renewable Energy
Location
CSU 255
Start Date
12-4-2022 1:30 PM
End Date
12-4-2022 2:30 PM
Student's Major
Mathematics and Statistics
Student's College
Science, Engineering and Technology
Mentor's Name
Iresha Premarathna
Mentor's Department
Mathematics and Statistics
Mentor's College
Science, Engineering and Technology
Description
Renewable energy sources are promising alternatives to fossil fuels (non-renewable energy). Renewable energy sources are clean, sustainable, safe, and environmentally friendly with little or no CO2 emissions. This reduces the dependence on fossil fuels, which in turn reduces environmental pollution. However, unpredictability in renewable energy sources such as solar and wind energy makes relying on these alternatives challenging. The data have been collected from www.eia.gov. It is based on monthly data from January 1973 to September 2021, and we obtain forecasts for the next 14 months (October 2021 to Nov 2022). This project aims to develop a model that can accurately forecast the future production and consumption of renewable energy in the United States. We utilize Autoregressive Integrated Moving Average (ARIMA) Model for modeling. Holt-Winters exponential method has been used for forecasting, found within the forecast package in R/RStudio. Finally, model validations have been tested using both visual (residual plots) and analytical (using p-values) methods.
Modeling and Forecasting Renewable Energy
CSU 255
Renewable energy sources are promising alternatives to fossil fuels (non-renewable energy). Renewable energy sources are clean, sustainable, safe, and environmentally friendly with little or no CO2 emissions. This reduces the dependence on fossil fuels, which in turn reduces environmental pollution. However, unpredictability in renewable energy sources such as solar and wind energy makes relying on these alternatives challenging. The data have been collected from www.eia.gov. It is based on monthly data from January 1973 to September 2021, and we obtain forecasts for the next 14 months (October 2021 to Nov 2022). This project aims to develop a model that can accurately forecast the future production and consumption of renewable energy in the United States. We utilize Autoregressive Integrated Moving Average (ARIMA) Model for modeling. Holt-Winters exponential method has been used for forecasting, found within the forecast package in R/RStudio. Finally, model validations have been tested using both visual (residual plots) and analytical (using p-values) methods.
Recommended Citation
Sanjel, Deepshikha. "Modeling and Forecasting Renewable Energy." Undergraduate Research Symposium, Mankato, MN, April 12, 2022.
https://cornerstone.lib.mnsu.edu/urs/2022/oral-session-04/3
