Inflation and Energy Prices

Esteves, Paulo Soares

doi:10.1016/b0-12-176480-x/00149-2

Cited by 2 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In light of all these evaluations regarding the importance of energy, it is seen that G7 countries, which consists of Canada, France, Germany, Italy, Japan, the United Kingdom, and the United States [13], have important collaborations in various fields, including energy efficiency, to achieve energy security [14]. This collaboration is not only crucial for ensuring a stable and sustainable energy supply but also for mitigating the impacts of climate change.…”

Section: Introductionmentioning

confidence: 99%

Forecasting of G7 Countries' Total Energy Production: A Rigorous Exploration with Artificial Neural Networks and Multiple Linear Regression

BAYIR,

KILIÇ,

DİRİ

et al. 2024

Preprint

View full text Add to dashboard Cite

The G7 countries, consisting of Canada, France, Germany, Italy, Japan, the United Kingdom, and the United States, have important collaborations in energy production to achieve energy security. One of the main systems of Artificial intelligence's, artificial neural networks (ANN), is crucial to this area of study, comparatively using Multiple Linear Regression (MLR) comparatively. ANN and MLR are feasible to use across the G7 countries' total energy production numbers, and these numbers were determined using ANN and MLR forecasting techniques. The data included the years 1990–2020, focusing on GDP intensity, refined oil product production, electricity production, and renewable energy proportion. In ANN modeling, the best regression results at 10*10 have been obtained with two hidden layers. All regression values were 0.99947, with the training regression value being 0.99912, the validation regression value being 0.99997, and the test regression value being 0.99997. The results showed high accuracy, with regression scores exceeding 99% and smaller prediction error values. A paired sample t test has been applied to see whether the distinction between the average values is significant or not. The results of the test between the actual and predicted values (p = 0.7462 > 0.05) revealed that the forecasted values have been quite close to the actual values. Total energy production Mean Absolute Deviation (MAD), Mean Squared Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) parameters have been calculated as 4.364, 34.072, 5.837, and 0.162, respectively. The research proved that ANNs are effective in forecasting total energy output. And, with MLR, error values for MAD, MSE, RMSE, and MAPE were also found to be 5.364, 34.352, 5.861, and 1.609, respectively, using MLR modeling. By 2035, the G7 nations are expected to produce 50,652.746 Mtoe of energy collectively. The research proved that ANNs are effective in forecasting total energy output.

show abstract

Section: Introductionmentioning

confidence: 99%