Bayesian networks based policy making in the renewable energy sector

Abstract

Extensive research on energy policy nowadays combines theory with advanced statistical tools such as Bayesian networks for analysis and prediction. The majority of these studies are related to observe energy scenarios in various economic or social conditions, but only a few of them target the renewable energy sector. Therefore, it is crucial to design a method to understand the causal relationships between variables such as consumption, greenhouse emissions, investment in renewables and investment in fossil fuels. This research paper aims to present expert models using the capabilities of Bayesian networks in the renewable energy sector, considering renewables in two countries: Germany and Italy. For this purpose, expert models are built in BayesiaLab with supervised learning. An augmented naïve model is applied to quantitative data consisting of the consumption rate of geothermal and hydro energy sectors. As a result, it is indicated that in the optimum case, geothermal and hydro energy consumption will be increased in parallel with investment. It is found that, as oil price grows, greenhouse emissions will decrease. The precision of the expert model is no less than 90%. Copyright © 2020 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved