Elektrik ve Enerji Bölümü Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12514/195

Browse

Now showing 1 - 6 of 6

A hybrid approach consisting of 3D depthwise separable convolution and depthwise squeeze‑and‑excitation network for hyperspectral image classifcation
(Earth Science Informatics, 2024) Güngör, Mustafa; Güngör, Mustafa
Hyperspectral image classifcation is crucial for a wide range of applications, including environmental monitoring, precision agriculture, and mining, due to its ability to capture detailed spectral information across numerous wavelengths. However, the high dimensionality and complex spatial-spectral relationships in hyperspectral data pose signifcant challenges. Deep learning, particularly Convolutional Neural Networks (CNNs), has shown remarkable success in automatically extracting relevant features from high-dimensional data, making them well-suited for handling the intricate spatial-spectral relationships in hyperspectral images.This study presents a hybrid approach for hyperspectral image classifcation, combining 3D Depthwise Separable Convolution (3D DSC) and Depthwise Squeeze-and-Excitation Network (DSENet). The 3D DSC efciently captures spatial-spectral features, reducing computational complexity while preserving essential information. The DSENet further refnes these features by applying channel-wise attention, enhancing the model's ability to focus on the most informative features. To assess the performance of the proposed hybrid model, extensive experimental studies were carried out on four commonly utilized HSI datasets, namely HyRANK-Loukia and WHU-Hi (including HongHu, HanChuan, and LongKou). As a result of the experimental studies, the HyRANK-Loukia achieved an accuracy of 90.9%, marking an 8.86% increase compared to its previous highest accuracy. Similarly, for the WHU-Hi datasets, HongHu achieved an accuracy of 97.49%, refecting a 2.11% improvement over its previous highest accuracy; HanChuan achieved an accuracy of 97.49%, showing a 2.4% improvement; and LongKou achieved an accuracy of 99.79%, providing a 0.15% improvement compared to its previous highest accuracy. Comparative analysis highlights the superiority of the proposed model, emphasizing improved classifcation accuracy with lower computational costs.
Analysis and Mitigation of Power Quality Issues in Distributed Generation Systems Using Custom Power Devices
(IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2018) Hossain, Eklas; Tur, Mehmet Rida; Padmanaban, Sanjeevikumar; Ay, Selim; Khan, Imtiaj
This paper discusses the power quality issues for distributed generation systems based on renewable energy sources, such as solar and wind energy. A thorough discussion about the power quality issues is conducted here. This paper starts with the power quality issues, followed by discussions of basic standards. A comprehensive study of power quality in power systems, including the systems with dc and renewable sources is done in this paper. Power quality monitoring techniques and possible solutions of the power quality issues for the power systems are elaborately studied. Then, we analyze the methods of mitigation of these problems using custom power devices, such as D-STATCOM, UPQC, UPS, TVSS, DVR, etc., for micro grid systems. For renewable energy systems, STATCOM can be a potential choice due to its several advantages, whereas spinning reserve can enhance the power quality in traditional systems. At Last, we study the power quality in dc systems. Simpler arrangement and higher reliability are two main advantages of the dc systems though it faces other power quality issues, such as instability and poor detection of faults.
Analysis of Open Circuit Voltage MPPT Method with Analytical Analysis with Perturb and Observe (P&O) MPPT Method in PV Systems
(Taylor and Francis Ltd., 2023) Çakmak, Fevzi; Tür, Mehmet Rıda; Tür, Mehmet Rıda
This study conducts a comprehensive comparison between two prominent Maximum Power Point Tracking (MPPT) techniques employed in solar energy systems: the Perturb and Observe (P&O) method and the Analytical Solution Fractional Open Circuit Voltage (ASFOCV) method. To assess the effectiveness of these MPPT approaches, a simulation study was conducted using four SHARP NDQ295 model photovoltaic panels, configured as two panels in series and two in parallel. Both the P&O and ASFOCV MPPT methods were evaluated under various scenarios of radiation levels and temperature changes. The results unequivocally demonstrate the superior performance of the ASFOCV MPPT method over the P&O MPPT method. The ASFOCV method notably enhanced converter output power by up to 5% when compared to the P&O method, leading to more efficient energy production. Furthermore, the ASFOCV method exhibited rapid stabilization of output voltage during abrupt weather changes, outperforming the P&O method in this regard. This study underscores the potential of the ASFOCV MPPT method to enhance the efficiency of solar energy systems and its adaptability to fluctuating environmental conditions. Future research endeavors could focus on mitigating the ASFOCV method’s sensitivity to temperature variations and conducting real-world applications to further investigate its performance under practical circumstances.
Distributed generation system planning based on renewable energy source
(IEEE, 2022) Çakmak, Fevzi; Tür, Mehmet Rıda; Çakmak, Fevzi; Atiç, Serdal; Tür, Mehmet Rıda; Bayindir, Ramazan
Distributed generation systems are needed in order to use existing energy resources efficiently and to meet energy needs. Although the interconnection of distributed generation systems with renewable sources offers many advantages, technical difficulties may arise from the inappropriate integration of distributed generation. Therefore, optimal planning of distributed generation is very important for the distributed grid to provide the expected power. Optimizing production systems is used to increase efficiency, provide flexibility in electrical systems, reduce costs and reduce power fluctuations. Meta-heuristic algorithms are more suitable for multi-purpose applications. In this study, the renewable energy source and energy storage system in the distributed generation system are also mentioned. Some of the optimization methods used for optimal planning of the distributed system are also included.
Learning-Based Approaches for Voltage Regulation and Control in DC Microgrids with CPL
(Multidisciplinary Digital Publishing Institute, 2023) Güngör, Mustafa; Asker, Mehmet Emin
This article introduces a novel approach to voltage regulation in a DC/DC boost converter. The approach leverages two advanced control techniques, including learning-based nonlinear control. By combining the backstepping (BSC) algorithm with artificial neural network (ANN)-based control techniques, the proposed approach aims to achieve accurate voltage tracking. This is accomplished by employing the nonlinear distortion observer (NDO) technique, which enables a fast dynamic response through load power estimation. The process involves training a neural network using data from the BSC controller. The trained network is subsequently utilized in the voltage regulation controller. Extensive simulations are conducted to evaluate the performance of the proposed control strategy, and the results are compared to those obtained using conventional BSC and model predictive control (MPC) controllers. The simulation results clearly demonstrate the effectiveness and superiority of the suggested control strategy over BSC and MPC.
Mppt Control for PV Systems with Analytical Analysis Fractional Open Circuit Voltage Method
(IEEE, 2022) Çakmak, Fevzi; Tür, Mehmet Rıda; Tür, Mehmet Rıda
Abstract— In this study, analytical resolved fractional open circuit voltage (FOCV) maximum power point tracking (MPPT) method is presented. The proposed method is obtained by calculating it by utilizing the single diode circuit of the PV module, while measuring the open circuit voltage (Voc) by interrupting the power of other open circuit voltage methods. Vmpp is obtained by multiplying the obtained Voc voltage with the coefficient. The voltage variation (E) is obtained by the subtraction between the panel voltage (Vpv) and the Vmpp voltage. It is applied as an input to the PI controller by multiplying the Ki factor to limit the voltage variation (E). The PI Controller generates the required duty cycle for the DC-DC converter. The most important advantage of this method is acquaring open circuit voltage without power interruption. The proposed method operated effectively at different radiation and temperature values. For the proposed method, it has simulated in Matlab/Simulink program using SHARP NDQ295 model PV panel.

Browse

Browsing Elektrik ve Enerji Bölümü Koleksiyonu by Language "en"