Yazar "Aygul, Kemal" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • [ X ]
    Öğe
    A new method for generating short-term power forecasting based on artificial neural networks and optimization methods for solar photovoltaic power plants
    (Springer Verlag, 2019) Demirdelen, Tugce; Ozge Aksu, Inayet; Esenboga, Burak; Aygul, Kemal; Ekinci, Firat; Bilgili, Mehmet
    In recent times, solar PV power plants have been used worldwide due to their high solar energy potential. Although the PV power plants are highly preferred, the main disadvantage of the system is that the output power characteristics of the system are unstable. As PV power plant system is connected to the grid side, unbalanced power flow effects all systems controls. In addition, the load capacitys is not exactly known. For this reason, it has become an important issue to be known correctly in PV output power and their time-dependent changes. The main aim of this work is to eliminate power plant instability due to the output power imbalance. For the short-term, power prediction is estimated by real-time data of 1 MW PV power plant in use. Estimation power data are compared with real-time data and precision of the proposed method is demonstrated. In the first phase, traditional artificial intelligence algorithms are used. Then, these algorithms are trained with swarm based optimization methods and the performance analyses are presented in detail. Among all the algorithms used, the algorithm with the lowest error is determined. Thus, this study provides useful information and techniques to help researchers who are interested in planning and modeling PV power plants. © Springer Nature Singapore Pte Ltd. 2019.
  • [ X ]
    Öğe
    A novel hybrid metaheuristic optimization method to estimate medium-term output power for horizontal axis wind turbine
    (Sage Publications Ltd, 2019) Ekinci, Firat; Demirdelen, Tugce; Aksu, Inayet Ozge; Aygul, Kemal; Esenboga, Burak; Bilgili, Mehmet
    The increasing damage caused by fossil fuels has made it a necessity for new and clean energy sources. In recent years, the use of wind energy from renewable energy sources has increased, which is a new and clean energy source. Wind energy is everywhere in nature. The wind speed changes depending on time. Thus, the wind power is unstable. In order to keep this disadvantage at a minimum level, future power estimation studies have been carried out. In these studies, different methods and algorithms are applied to estimate short and medium term in wind power. In this study, artificial neural network, particle swarm optimization and firefly algorithm (FA) as a new method are used for the first time in predicting wind power. As input data, temperature, wind speed and rotor speed the data recorded in the SCADA in wind turbines are used to predict medium-term wind speed and also wind power. Each method is compared in detail and their performances are revealed.
  • [ X ]
    Öğe
    Butterfly optimization algorithm based maximum power point tracking of photovoltaic systems under partial shading condition
    (Taylor & Francis Inc, 2023) Aygul, Kemal; Cikan, Murat; Demirdelen, Tugce; Tumay, Mehmet
    Because of dust, trees, high buildings in the surrounding area, partial shading conditions (PSC) occur in photovoltaic (PV) systems. This condition affects the power output of the PV system. Under PSC there is a global maximum power point (GMPP) besides there are a few local maximum power points (LMPP). This condition makes the maximum power point tracking (MPPT) procedure a challenging task. In order to solve this issue, soft computing techniques such as gray wolf optimization (GWO), particle swarm optimization (PSO) and Gravitational Search Algorithm (GSA) are implemented. However, the performance of MPP trackers still needs to be improved. The main contribution of this paper is improving the tracking speed by implementing BOA to the MPPT of the PV system under PSC. Thus, in real-time applications a promising alternative presented to the literature to improve the performance of the PV systems under variable PSC because of its fast tracking speed. PV system consists of PV array, boost converter and load are modeled and simulated in MATLAB/Simulink. BOA algorithm is implemented for three different insolation scenarios on the PV array. The results of the BOA algorithm verified by a comparative analysis with PSO-GSA and GWO algorithms. The results show that BOA can give high accuracy and better tracking speed than these algorithms in recent literature.