Yazar "Kul, Seda" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim
    Öğe
    A machine learning-based real-time remaining useful life estimation and fair pricing strategy for electric vehicle battery swapping stations
    (İeee-Inst Electrical Electronics Engineers İnc, 2025) Çeltek, Seyit Alperen; Kul, Seda; Polat, A. Ozgur; Zeinoddini-Meymand, Hamed; Shahnia, Farhad
    The increasing adoption of electric vehicles (EVs) has led to the widespread implementation of battery swapping stations. However, ensuring fairness in battery pricing remains a significant challenge since variations in battery health and performance among swapped batteries can result in user dissatisfaction and operational inefficiencies. This paper introduces a novel approach to enhance fairness in battery swapping by integrating a machine learning-based real-time prediction model with a pricing strategy based on remaining useful life (RUL) estimation to address this issue. The proposed solution comprises a real-time RUL estimation system and a dynamic pricing mechanism that ensures fair pricing based on battery health and performance. This integrated approach aims to improve user satisfaction and the operational efficiency of swapping stations. The paper evaluates various machine learning algorithms for real-time RUL estimation regarding accuracy, computation time, and memory usage. The results suggest that XGBoost provides the most suitable balance between accuracy and efficiency, making it an effective solution for real-world applications. Comparative analysis shows that the XGBoost model outperforms the second-best method (Random Forest) with a lower error (3.50 vs 3.79) while maintaining competitive computational efficiency (9.75 vs 8.52 seconds) and memory usage (2.12 vs 2.32 MB) when solving a typical numerical case study problem. The proposed approach has the potential to accelerate the adoption of electric vehicles and contribute to sustainability goals by promoting efficient battery utilization and fair pricing mechanisms.
  • Küçük Resim
    Öğe
    Estimating wind speed with ANFIS: A case study in Karaman city
    (Karamanoğlu Mehmetbey Üniversitesi, 2024) Gulhan, Selim; Kul, Seda; Balcı, Selami; Çeltek, Seyit Alperen
    Wind energy, one of the renewable energy sources, plays an increasingly important role in our world as a clean and sustainable energy source. Since the electricity generation potential from wind energy has a variable structure, energy generation estimates to be made to minimize the adverse effects of this situation have an important place for both power plants and operators. Various estimation methods are used for wind energy sources. In this study, wind speed (m/s) is estimated using fuzzy logic, one of the 34902 data Adaptive-Network-Based Fuzzy Inference System (ANFIS) models consisting of hourly average temperature (℃), relative humidity (%), and actual pressure (hPa) parameters are taken at Karaman-17246 Meteorology Station in 2022. The Root Mean Square Error (RMSE) of the obtained results is examined, and it is seen that the method used approached the result with 0.97. Thus, the technical information is presented for researchers to determine the wind energy potential for the Karaman region in Turkiye.
  • Küçük Resim
    Öğe
    Parameter extraction of PV solar cell using metaheuristic methods
    (2023) Celtek, Seyit Alperen; Kul, Seda
    Due to the increasing crises in energy and environmental factors, the importance of renewable energy is increasing. However, it is gaining importance in developing photovoltaic energy systems. Therefore, great efforts are made to maximize success in accurately modeling PV parameters. Parameter estimation is a complex problem and requires advanced design tools such as optimization techniques because the current voltage (I–V) characteristics of PVs are nonlinear. This study investigates the best technique for the most accurate estimation of the parameters obtained in single-diode and double-diode cases. The Gray Wolf Optimization (GWO), Improved Gray Wolf Optimization (IGWO), Sine Cosine Algorithm (SCA), Whale Optimization Algorithm (WOA), and Multi-Verse Optimizer (MVO) are the algorithms used in this paper. Apart from the literature, this study considers that the PV parameter extraction problem is not just an offline optimization problem but also a real-time optimization issue. The performance of all methods has been compared with experimental data. The lowest error on minimum iteration and highest convergence accuracy have been achieved for offline optimization by using IGWO. The results clearly state that the IGWO is not usable in real-time applications even though IGWO is the best optimizer in offline optimization.
  • Küçük Resim
    Öğe
    Power quality enhancement of rectifiers of water electrolysis for the green hydrogen
    (IEEE, 2024) Kul, Seda; Balcı, Selami; Çeltek, S. Alperen; Polat, A. Özgür
    Electrolysis, a clean and efficient method, utilizes renewable alternating current (AC) for water decomposition into hydrogen. This study addresses power quality improvement in rectifiers converting renewable AC to direct current (DC) for electrolysis. This study focuses on improving the power quality of rectifiers used to convert AC from renewable energy sources into a DC source for hydrogen production in water electrolysis systems. For this purpose, the 12-pulse topology, using two interconnected 6-pulse rectifiers, delivers a smoother DC output with reduced ripple and improved mains current quality. This significantly minimizes harmonics, achieving a waveform closer to a pure sine wave without additional filtering. This approach offers a promising solution to mitigate power quality issues in renewable hydrogen production systems.