Repozytorium publikacji - Politechnika Gdańska

This study assessed the usefulness of algorithms in estimating energy consumption and carbon dioxide emissions in Viet- nam, in which the training dataset was used to train the models linear regression, random forest, XGBoost, and AdaBoost, allowing them to comprehend the patterns and relationships between population, GDP, and carbon dioxide emissions, energy consumption. The results revealed that random forest, XGBoost, and AdaBoost outperformed linear regression. Furthermore, for random forest, XGBoost, and AdaBoost, the coefficients of determination were higher, indicating a better fit to the data. Moreover, time series forecasting models such as autoregressive integrated moving average, seasonal autore- gressive integrated moving average, and exponential smoothing were used to predict future energy consumption and carbon dioxide emissions in Vietnam. The models were trained and verified using historical data. The time series model findings showed that energy consumption rose steadily during the predicted timeframe. The autoregressive integrated moving aver- age model predicted 162258.77 ktoe of energy use by 2050, whereas the seasonal autoregressive integrated moving average and exponential smoothing modes predicted 160673.8 ktoe and 153206.44 ktoe of energy use, respectively. By 2050, the autoregressive integrated moving average model anticipated 6.51 metric tons of carbon dioxide emissions per capita, the SARIMA model 7.769 metric tons, and the exponential smoothing model 6.22 metric tons. The findings show how machine learning techniques and time series models may be used to estimate energy usage and carbon dioxide emissions in Vietnam. These insights could assist Vietnam government in making informed judgments concerning energy planning and policy development

Autorzy

• Thanh Tuan Le,
• Prabhakar Sharma,
• Sameh M. Osman,
• dr hab. inż. Marek Dzida link otwiera się w nowej karcie ,
• Phuoc Quy Phong Nguyen,
• Minh Ho Tran,
• Dao Nam Cao,
• Viet Dung Tran