The utilization of renewable energy sources (RES) has become inevitable, not only due to the increasing scarcity of fossil fuels, but also to sustain life on Earth. Consequently, countries have started developing renewable energy policies individually and as part of global organizations and networks, such as the Organization for Economic Co-operation and Development (OECD), the European Union (EU) and the International Energy Agency (IEA). Turkey is a developing OECD member country and in the accession process to the EU. Thus, the renewable energy policies should be aligned with those of the EU. Moreover, despite the substantial amount and wide range of RES, it is still in a position to import more than half of its energy demand. In the light of these facts, this study aims to analyze and compare the renewable energy policies in Turkey with those adopted worldwide to lay out possible solutions regarding its energy problems.
1 January 2022 in Black Sea Journal of Engineering and Science
The increasing demand for renewable energy sources attract attention of both researchers and governments. The countries support renewable energy and technologies developed for the efficient use of renewable energy. For this reason, the assessment and prediction of renewable energy consumption is vital for governments. Furthermore, associations put forward long-term and short-term targets for countries. Therefore, European Union (EU) members provide support schemes for promoting renewable energy consumption. In this study, renewable energy consumption in EU is predicted using artificial neural networks. The World Development indicators which are renewable electricity output, energy use generated from combustible renewables and waste, electricity production from oil, gas and coal sources, energy use generated from alternative and nuclear energy, electricity production from renewable sources excluding hydroelectric, energy imports, energy use, gross domestic product (GDP) and population are evaluated as independent variables using historical data from 1990 to 2015. The results indicate that artificial neural networks provides convenient results in energy demand forecasting as seen in similar studies of the literature.