Abstract:

In addition to the country’s economy and prosperity level, energy planning is of great importance in terms of defence security and strategic goals. Therefore, the most accurate estimate of energy demand is a critical issue in terms of country policies. In recent years, a variety of methods have been used to be able to predict the level of future energy demand in the most accurate way. However, it is necessary to choose the most suitable among the different methods of prediction. In this study, a hybrid method for modeling and predicting the annual transport-based energy demand (UKET) in Turkey has been used together with the Adaptive-Network Based Fuzzy Inference Systems (ANFIS) and the Particle Bulk Optimization (PSO) algorithm. In the development of the models, the non-clean domestic taxation (GDP), the population, the annual total vehicle-km parameters and the number of vehicles in the annual traffic were taken as the model input. Data between 1970 and 2016 were used for the training and testing stages of the models. The ANFIS-PSO model, defined as the best approach, has been used for the UKET forecast of Turkey from 2017 to 2023. The results showed that Turkey’s demand for transport-based energy will increase by about 1.2 times the value in 2016 over a seven-year period.

Keywords: