Yazar "Tasdemir, Beste Desticioglu" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Capacited range coverage location model for electric vehicle charging stations: A case of Istanbul-Ankara highway
    (Elsevier, 2025) Tasdemir, Beste Desticioglu; Koc, Erdinc; Simsek, Ahmed Ihsan
    It is clear that the rate of use of electric vehicles is increasing day by day due to growing environmental concerns of consumers, scarcity of natural resources, increasing awareness of renewable energy sources, following technological progress, and the cost advantage it has for individual or corporate users. One of the most important drawbacks of electric vehicles is their low range. With the studies carried out in battery technology, it is aimed to increase the range distance. However, when the range distances of today's electric vehicles considered, vehicle owners demand to recharge as soon as possible on long distances. While electric vehicle owners have the opportunity to perform many activities during charging in the city, they do not have such opportunities in intercity traffic such as on highways. For this reason, the waiting times for charging stations on intercity roads should be reduced and their availability should be increased. In this study, the Istanbul-Ankara highway, one of the most frequently used highways in Turkey, is considered. It is aimed to reach the minimum number of charging stations that meet the assumptions. The capacited range coverage location model is used to solve a real-life problem by considering the distances between fuel stations and resting facilities on this highway. With the modifications made to the base model, the obtained model has become more suitable for use in real life problems. With the results obtained, it is stated in which gas station or resting facility charging stations should be installed on the highway.
  • Küçük Resim Yok
    Öğe
    Deep Learning Forecasting Model for Market Demand of Electric Vehicles
    (Mdpi, 2024) Simsek, Ahmed Ihsan; Koc, Erdinc; Tasdemir, Beste Desticioglu; Aksoz, Ahmet; Turkoglu, Muammer; Sengur, Abdulkadir
    The increasing demand for electric vehicles (EVs) requires accurate forecasting to support strategic decisions by manufacturers, policymakers, investors, and infrastructure developers. As EV adoption accelerates due to environmental concerns and technological advances, understanding and predicting this demand becomes critical. In light of these considerations, this study presents an innovative methodology for forecasting EV demand. This model, called EVs-PredNet, is developed using deep learning methods such as LSTM (Long Short-Term Memory) and CNNs (Convolutional Neural Networks). The model comprises convolutional, activation function, max pooling, LSTM, and dense layers. Experimental research has investigated four different categories of electric vehicles: battery electric vehicles (BEV), hybrid electric vehicles (HEV), plug-in hybrid electric vehicles (PHEV), and all electric vehicles (ALL). Performance measures were calculated after conducting experimental studies to assess the model's ability to predict electric vehicle demand. When the performance measures (mean absolute error, root mean square error, mean squared error, R-Squared) of EVs-PredNet and machine learning regression methods are compared, the proposed model is more effective than the other forecasting methods. The experimental results demonstrate the effectiveness of the proposed approach in forecasting the electric vehicle demand. This model is considered to have significant application potential in assessing the adoption and demand of electric vehicles. This study aims to improve the reliability of forecasting future demand in the electric vehicle market and to develop relevant approaches.