Filters

2013 - 201922020 - 20221
Reset filters

Settings

Department: Atılım UniversitySubject: Demand forecasting

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Article
    Citation - WoS: 45
    Citation - Scopus: 56
    Demand Forecast for Road Transportation Fuels Including Gasoline, Diesel, Lpg, Bioethanol and Biodiesel for Turkey Between 2013 and 2023
    (Pergamon-elsevier Science Ltd, 2014) Melikoglu, Mehmet
    In Turkey, more than 90% of passengers and goods are transported by roads. In order to flow this immense traffic nearly 2.7 million m(3) of gasoline, 11.5 million m(3) of diesel, and 5.2 million m(3) of liquefied petroleum gas (LPG) was consumed in 2011. Starting from 2013, Turkey plans to blend biofuels to gasoline and diesel gradually reaching to 10% (volume) by 2020. Turkey's economy has been growing at unprecedented rates since 2003. As a result, both diesel and LPG consumption reached to record levels. Yet, gasoline demand decreased almost linearly in the same period. Accordingly, forecasting road transportation fuel demand becomes more difficult and yet more important than ever before. Gasoline, diesel, LPG, bioethanol and biodiesel demand has been forecast for the first time in this study using semi-empirical models in the view of Turkey's Vision 2023 goals, Energy Market Regulatory Authority targets, and European Union directives. The models suggested that in 2023, annual gasoline consumption in Turkey could decrease below 2.0 million m(3), whereas, diesel and LPG consumption could rise to 16.4 and 8.8 million m(3), respectively. Consequently, 0.3 million m(3) of bioethanol and 1.4 million m(3) biodiesel could be required to fulfil the official targets in 2023. (C) 2013 Elsevier Ltd. All rights reserved.
  • Thumbnail Image
    Review
    Citation - WoS: 87
    Citation - Scopus: 95
    Vision 2023: Forecasting Turkey's Natural Gas Demand Between 2013 and 2030
    (Pergamon-elsevier Science Ltd, 2013) Melikoglu, Mehmet
    Natural gas is the primary source for electricity production in Turkey. However, Turkey does not have indigenous resources and imports more than 98.0% of the natural gas it consumes. In 2011, more than 20.0% of Turkey's annual trade deficit was due to imported natural gas, estimated at US$ 20.0 billion. Turkish government has very ambitious targets for the country's energy sector in the next decade according to the Vision 2023 agenda. Previously, we have estimated that Turkey's annual electricity demand would be 530,000 GWh at the year 2023. Considering current energy market dynamics it is almost evident that a substantial amount of this demand would be supplied from natural gas. However, meticulous analysis of the Vision 2023 goals clearly showed that the information about the natural gas sector is scarce. Most importantly there is no demand forecast for natural gas in the Vision 2023 agenda. Therefore, in this study the aim was to generate accurate forecasts for Turkey's natural gas demand between 2013 and 2030. For this purpose, two semi-empirical models based on econometrics, gross domestic product (GDP) at purchasing power parity (PPP) per capita, and demographics, population change, were developed. The logistic equation, which can be used for long term natural gas demand forecasting, and the linear equation, which can be used for medium term demand forecasting, fitted to the timeline series almost seamlessly. In addition, these two models provided reasonable fits according to the mean absolute percentage error, MAPE %, criteria. Turkey's natural gas demand at the year 2030 was calculated as 76.8 billion m(3) using the linear model and 83.8 billion m(3) based on the logistic model. Consequently, found to be in better agreement with the official Turkish petroleum pipeline corporation (BOTAS) forecast, 76.4 billion m(3), than results published in the literature. (C) 2013 Elsevier Ltd. All rights reserved.
  • Thumbnail Image
    Article
    Citation - WoS: 8
    Citation - Scopus: 11
    A Study of Load Demand Forecasting Models in Electricity Using Artificial Neural Networks and Fuzzy Logic Model
    (Materials & Energy Research Center-merc, 2022) Al-ani, B. R. K.; Erkan, E. T.
    Since load time series are very changeable. demand forecasting of the short-term load is challenging based on hourly, daily, weekly, and monthly load forecast demand. As a result, the Turkish Electricity Transmission Company (TEA) load forecasting is proposed in this paper using artificial neural networks (ANN) and fuzzy logic (FL). Load forecasting enables utilities to purchase and generate electricity, load shift, and build infrastructure. A load forecast was classified into three sorts (hourly, weekly and monthly). Over time, forecasting power loads with artificial neural networks and fuzzy logic reveals a massive decrease in ANN and a progressive increase in FL from 24 to 168 hours. As illustrated, fuzzy logic and artificial neural netANorks outperform regression algorithms. This study has the highest growth and means absolute percentage error (MAPE) rates compared to FL and ANN. Although regression has the highest prediction growth rate, it is less precise than FL and ANN due to their lower MAPE percentage. Artificial Neural Networks and Fuzzy Logic are emerging technologies capable of forecasting and mitigating demand volatility. Future research can forecast various Turkish states using the same approach.