Bhuiyan, M.M.H.; Sakib, A.N.; Alawee, S.I.; Razzaghi, T. Fueling the Future: A Comprehensive Analysis and Forecast of Fuel Consumption Trends in U.S. Electricity Generation. Sustainability2024, 16, 2388.
Bhuiyan, M.M.H.; Sakib, A.N.; Alawee, S.I.; Razzaghi, T. Fueling the Future: A Comprehensive Analysis and Forecast of Fuel Consumption Trends in U.S. Electricity Generation. Sustainability 2024, 16, 2388.
Bhuiyan, M.M.H.; Sakib, A.N.; Alawee, S.I.; Razzaghi, T. Fueling the Future: A Comprehensive Analysis and Forecast of Fuel Consumption Trends in U.S. Electricity Generation. Sustainability2024, 16, 2388.
Bhuiyan, M.M.H.; Sakib, A.N.; Alawee, S.I.; Razzaghi, T. Fueling the Future: A Comprehensive Analysis and Forecast of Fuel Consumption Trends in U.S. Electricity Generation. Sustainability 2024, 16, 2388.
Abstract
The U.S. Energy Information Administration (EIA) provides crucial data on monthly and annual fuel consumption for electricity generation. This data covers significant fuels such as coal, petroleum liquids, petroleum coke, and natural gas. Fuel consumption patterns are highly dynamic, influenced by diverse factors. Understanding these fluctuations is essential for effective energy planning and decision-making. This study outlines a comprehensive analysis of fuel consumption trends in electricity generation. Utilizing advanced statistical methods, including time series analysis and autocorrelation, our objective is to uncover intricate patterns and dependencies within the data. This paper aims to forecast fuel consumption trend for electricity generation using data from 2015 to 2022. Several time-series forecasting models, including all four benchmark methods (Mean, Naïve, Drift, and seasonal Naïve), Seasonal and Trend Decomposition using Loess (STL), Exponential Smoothing (ETS), and Autoregressive Integrated Moving Average (ARIMA) methods, have been applied. The best-performing models are determined based on Root Mean Squared Error (RMSE) values. For Natural Gas (NG) consumption, the ETS model achieves the lowest RMSE of 20,687.46. STL demonstrates the best performance for coal consumption with an RMSE of 5,936.203. The seasonal Naïve (SNaïve) model outperforms others for petroleum coke forecasting, yielding an RMSE of 99.49. Surprisingly, the Mean method has the lowest RMSE of 287.34 for petroleum liquids, but the ARIMA model is reliable for its ability to capture complex patterns. Residual plots are analyzed to assess the models' performance against statistical parameters. Accurate fuel consumption forecasting is very important for effective energy planning and policymaking. The findings from the study help policymakers strategically allocate resources, plan infrastructure development and support economic growth.
Keywords
Fuel Consumption; Forecasting; Time Series Analysis; Sustainable Energy Policies; RMSE.
Subject
Engineering, Energy and Fuel Technology
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
