Analyzing of Renewable and Non-Renewable Energy consumption via Bayesian Inference

Abstract Excessive use of fossil fuels which consist largely of carbon and hydrogen, threatens the global climate, ecosystem, and public health. Substitution of renewable energy into fossil fuel energy will slow the rate of environmental degradation, reduce air pollution, and greenhouse gas emission. This study uses an econometrics approach to forecast the energy consumption of the Japan until 2030. Then, it applies a stochastic substitution model, to fit suitable renewable energy model. Essential part of the proposed model relies on the recursive Bayesian filter and the Random Number generation to update the distribution of renewable energy model through substitution. Four scenarios are defined in terms of the two parameters of the posterior distribution (mean, and standard deviation). The results of the proposed model demonstrate error reduction of the proposed model compared with the first-order exponential smoothing model. Moreover, the random data generated to forecast the renewable energy consumption demonstrate a constant growth for the year 2028 and 2029.