Yazar "Cubukcu, Mete" seçeneğine göre listele

Listeleniyor 1 - 7 / 7
  • Küçük Resim Yok
    Öğe
    Effect of Using Photovoltaic Power Systems in Sustainable Energy Action Plan of a Big County Municipality in Turkey
    (Springer International Publishing Ag, 2020) Biter, Mert; Cubukcu, Mete
    Integration of solar photovoltaic energy systems to urban planning is one of the key priorities of local authorities who cares the global warming threat. "Covenant of Mayors" (CoM), which is the most extensive association of local governments in the world, has started serious works on fighting against climate change and required the local governments' preparation of sustainable energy action plans (SEAP). Bornova Municipality has calculated its reference greenhouse gas emission inventory as 31,432 t CO(2)e (CO2 equivalent) in the SEAP delivered to the CoM on February 7th, 2013. in accordance with the CoM goal, it has committed to reduce its greenhouse gas emission value by 25% by 2020 and realized the installation of a 300 kWp photovoltaic power system (PVPS) in 2013 as the most important project. the main objective of this study is to use the real-time data of 300 kWp plant and evaluate its contribution to the reduction of greenhouse gas emission. Moreover, usable potential roof surface areas of the service buildings of Bornova Municipality have been calculated and the contribution of the increase of the PVPS capacity to the goal of greenhouse gas emission reduction by 2020 has been studied.
  • Küçük Resim Yok
    Öğe
    Exergetic performance of building attached photovoltaic power plant: a case study for an olive oil production corporation
    (Inderscience Enterprises Ltd, 2019) Bozoglan, Elif; Cubukcu, Mete; Saglam, Eylem; Ogutcen, A. Evren
    It is known that solar energy is among the most available and sustainable renewable sources of energy. This study utilised energy and exergy analyses to assess the performance of a building attached photovoltaic (BAPV) plant. The grid connected BAPV plant installed on the roof of an olive oil production company situated in Izmir, Turkey with a capacity of 701.2 kWp. Strings having a total of 21 monocrystalline solar modules constitute the BAPV system. In 2017, the plant was found to have an exergy efficiency around 12.49-15.76% while it was discovered that the sustainability indexes of the BAPV plant were in the region of 1.14-1.19. The module plane and the electricity produced, recorded annual solar irradiation of 1,561.32 kWh/(m(2)y) and 878.29 MWh/y, respectively. As a result of the values, this study recorded a mean annual electricity specific yield of 1,252.55 kWh/kWp and performance ratio of 81.86%.
  • Küçük Resim Yok
    Öğe
    Implementation of Caputo type fractional derivative chain rule on back propagation algorithm
    (Elsevier, 2024) Candan, Mucahid; Cubukcu, Mete
    Fractional gradient computation is a challenging task for neural networks. In this study, the brief history of fractional derivation is abstracted, and the core framework of the Fa & agrave; di Bruno formula is implemented to the fractional gradient computation problem. As an analytical approach to solve the chain rule problem of fractional derivatives, the use of the Fa & agrave; di Bruno formula for the Caputo-type fractional derivative is proposed. When the fractional gradient is calculated using the proposed approach, the problem of determining the bounds of the formula for calculating the Caputo derivative is addressed. As a consequence, the fundamental problem with the fractional back-propagation algorithm is solved analytically, paving the way for the use of any differentiable and integrable activation function in case they are stable. The development of the algorithm and its practical implementation on the photovoltaic fault detection data-set is investigated. The reliability of the neural network metrics is also investigated using analysis of variance (ANOVA), the results are then presented to decide which are the best metrics and the best fractional order. Ordinary back-propagation, fractional back-propagation with and without L 2 regularization and momentum are presented in the results to show the advantages of using L 2 regularization and momentum in fractional order gradient. Consequently, the test metrics are reliable but cannot be separated from each other. By changing the batch size from 2 to full batches, the proposed system performs better with bigger batches, but adaptive moment estimation (ADAM) performs better with small batches. The cross validation shows the performance of back propagate ion neural networks have better performance than the ordinary neural networks. It is interesting that the best order for a specific data-set cannot be determined because it depends on the batch size, number of epochs and the cross-validation folds .
  • Küçük Resim Yok
    Öğe
    Modeling, comparative simulation and practical performance analysis of a stand-alone PV hybrid power system in Turkey
    (Natl Inst Optoelectronics, 2013) Cubukcu, Mete; Colak, Metin
    This study aims to analyze and compare the performance of a stand-alone PV hybrid system located in Fethiye, Turkey. The system was built in off-grid configuration employing a wind turbine - diesel generator hybrid auxiliary supply. System performance was calculated both by simulation and real life measurements. Simulation results and actual performance has been compared for determining the factors affecting the overall performances of PV and/or hybrid power systems. The impact of the meteorological conditions, load demands, and the characteristics of system components were also analyzed. The results were reported using the international evaluation parameters.
  • Küçük Resim Yok
    Öğe
    Modeling, comparative simulation and practical performance analysis of a stand-alone PV hybrid power system in Turkey
    (Natl Inst Optoelectronics, 2013) Cubukcu, Mete; Colak, Metin
    This study aims to analyze and compare the performance of a stand-alone PV hybrid system located in Fethiye, Turkey. The system was built in off-grid configuration employing a wind turbine - diesel generator hybrid auxiliary supply. System performance was calculated both by simulation and real life measurements. Simulation results and actual performance has been compared for determining the factors affecting the overall performances of PV and/or hybrid power systems. The impact of the meteorological conditions, load demands, and the characteristics of system components were also analyzed. The results were reported using the international evaluation parameters.
  • Küçük Resim Yok
    Öğe
    Performance analysis of a grid-connected photovoltaic plant in eastern Turkey
    (Elsevier, 2020) Cubukcu, Mete; Gumus, Harun
    Photovoltaic market is a globally growing market, and this also reflects the current trend in Turkey. in this study, a grid-connected photovoltaic (PV) power plant of 2130.7 kWp rated power located in the eastern part of Turkey was analysed. The photovoltaic plant was assessed in terms of performance parameters such as reference yield, array yield, final yield, inverter efficiency, capture loss, system loss, system efficiency, capacity factor, performance ratio and annual final yield. in 2017, 3519.98 MWh of energy was generated by this PV plant. Mean final yield, mean performance ratio, system efficiency and capacity factor were found as 4.53 h/d, 81.15%, 13.18% and 18.86%, respectively. Besides the real-time analysis, a simulation of energy prediction and performance analysis were also done. A comparison with other PV plants located in different parts of the world lead to the conclusion that insolation and environmental conditions are the primary factors that affect PV plant performance.
  • Küçük Resim Yok
    Öğe
    A supervised ensemble learning method for fault diagnosis in photovoltaic strings
    (Pergamon-Elsevier Science Ltd, 2021) Kapucu, Ceyhun; Cubukcu, Mete
    This study proposes a fault diagnosis method based on the use of a machine learning (ML) technique called ensemble learning (EL) for photovoltaic (PV) systems. EL methods aim to obtain better general-izability and prediction accuracy than a single ML algorithm by combining the predictions of multiple algorithms. In this context, first the most relevant features are selected by using grid-search with cross-validation. Then each learning algorithm and the EL model that will combine them have been improved in terms of parameter optimization.& nbsp; Results show that, with the appropriate features and optimized parameters for each single learning algorithm and the EL model, the proposed method not only improves the classification performance but also has a strong generalization ability for PV system fault diagnosis.& nbsp; (c) 2021 Elsevier Ltd. All rights reserved.