OTOğuz Taşdemir

Oğuz Taşdemir

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Oğuz Taşdemir has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Recycling-Based Passive Cooling of PV Panels Using Copper and Aluminum Waste Particles: An Experimental Study

    by Müjdat Öztürk, Ramazan Kayabaşı, Oğuz Taşdemir

    The performance of photovoltaic (PV) modules decreases as operating temperatures rise, particularly under high solar irradiance during summer months. Passive cooling techniques, which operate without external energy input, offer an effective and low cost way to control module temperature and improve electrical output. This study experimentally evaluates two waste based passive cooling materials (aluminum shavings and thin copper fins) mounted on the rear surfaces of PV modules. Three identical 100W monocrystalline panels were tested simultaneously under the same environmental conditions. The first panel was a reference panel, the second panel was coated with aluminum shavings, and the third panel was equipped with thin copper fins recovered from waste capacitor components. These recycled materials were selected for their low cost, availability and high surface area to volume ratio, enabling enhanced convective heat transfer. Temperature, solar irradiance, voltage, current and electrical power were recorded in real time using a custom data acquisition system. During peak radiation hours, the aluminum and copper cooled panels exhibited temperature reductions of approximately 5°C and 8°C, respectively, compared with the reference panel. Correspondingly, the copper cooled panel achieved up to a 5% increase in daily energy output, while the aluminum cooled panel produced a 2–3% improvement. Overall, the results show that lightweight and recyclable passive cooling elements can significantly enhance PV performance without increasing structural load or energy consumption, offering a practical solution for sustainable PV operation in warming climates.

  • Open Access

    A Hybrid XGBoost-Based Model Optimized with AVOA for Photovoltaic Power Forecasting

    by Oğuz Taşdemir, İsmet Alagöz

    Accurate forecasting of photovoltaic (PV) power generation is of critical importance for grid stability, energy management, and production planning in renewable energy systems. However, the high variability of atmospheric conditions and sudden fluctuations in solar irradiance significantly limit the performance of conventional forecasting models. In this study, a hybrid photovoltaic power forecasting model based on the XGBoost algorithm, whose hyperparameters are optimized using the Artificial Vulture Optimization Algorithm (AVOA) and enhanced with the physics-based Radiation Stability and Efficiency Index (RSEI), designated as RSEI-XGBoost-AVOA, is proposed. The proposed approach provides a forecasting framework that is not only data-driven but also sensitive to physical processes by jointly modeling the temporal stability of solar irradiance and intraday generation dynamics. In this context, irradiance variability is represented through statistical measures, while intraday generation behavior is modeled using a sinusoidal efficiency function, and this structure is made more flexible through parameters optimized by AVOA. The model performance was evaluated separately for four different seasons using real data obtained from a 25 MW photovoltaic power plant in Türkiye. The results show that the proposed hybrid (RSEI-XGBoost-AVOA) model produces lower error values than both the standard XGBoost model and the AVOA-optimized model across all seasons. The Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) values of the model were obtained as 4.15% and 0.4157 MW in summer, 6.07% and 0.2574 MW in winter, 8.03% and 0.7343 MW in spring, and 8.51% and 0.6135 MW in fall, respectively. These findings demonstrate that the proposed approach provides stable and generalizable forecasting performance even under highly variable atmospheric conditions and can be used as an effective decision-support tool for photovoltaic grid integration, short-term generation planning, and real-time energy management applications.

  • Techno-Economic Optimization of Grid-Connected Hybrid Microgrids: A Hybrid PSO-GWO Approach for Izmir Province

    by Salih Ermiş, Oğuz Taşdemir

    The increasing utilization of renewable energy sources is crucial for ensuring energy supply security and reducing carbon emissions. However, the intermittent nature of solar and wind energy complicates their grid integration and optimal sizing. In this study, a techno-economic optimization was performed for a pilot microgrid system comprising 20 residences in Izmir, Turkey, using current market data and real-time meteorological data. For the optimal design of the system, a novel Hybrid PSO-GWO algorithm, which combines the strengths of PSO and GWO and possesses high capability to avoid local optima stagnation, is proposed. Two different scenarios, "Economic" and "Resilient", were analyzed within the scope of the study. Simulation results demonstrated that the PV/Grid combination is the most profitable option in the cost-oriented scenario, with a Net Present Cost (NPC) of 119,001 $ and a payback period of 3.2 years. In the scenario prioritizing energy security, battery and wind turbines were integrated into the system, ensuring uninterrupted energy supply with only a 10.8% increase in NPC (131,917 $). Furthermore, statistical analyses demonstrated that the proposed model performed better than standard methods. This study serves as an up-to-date reference for resilient and economic microgrid applications in Turkey's energy transition process.

  • Comparative Analysis of GA and PSO for PID Tuning in Wind Energy Systems

    by Oğuz Taşdemir, Nuri Alper Metin

    This study focuses on the optimization and comparative analysis of PID controller parameters for regulating the output voltage in a 100 kW wind energy conversion system (WECS) using heuristic algorithms. The system under investigation consists of a wind turbine, a Permanent Magnet Synchronous Generator (PMSG), a three-phase diode rectifier, a DC-DC boost converter, and an ohmic load. To maintain load voltage stability under varying wind speeds, the PID coefficients (Kp, Ki, Kd) used in the control of the boost converter is determined using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) methods. A standard objective function for minimizing error is defined for both algorithms. Simulation results performed in MATLAB/Simulink showed that both methods significantly improved system performance. Comparative analyses revealed that the PSO algorithm reached the reference voltage value faster than the GA, while the GA was more effective at minimizing oscillations around the reference value.

  • A Hybrid Deep Learning Model Integrating CNN–LSTM and Metaheuristic Optimization for Seasonal Wind Power Forecasting

    by Oğuz Taşdemir, Salih Ermiş

    This study introduces a medium-term wind power forecasting approach based on hybrid deep learning architectures integrating convolutional and recurrent neural networks with metaheuristic optimization. Three hybrid models CNN-LSTM, ISO-LSTM, and SO-LSTM were trained using 2024 daily meteorological and power data from a 52.80 MW wind farm in the Marmara Region of Turkey. Seasonal performance was evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) metrics. Among the models, CNN-LSTM achieved the highest accuracy, particularly in summer, with significantly lower error values (MAE = 9.02 MW, MAPE = 4.45%, RMSE = 10.52 MW). ISO-LSTM demonstrated moderate accuracy, while SO-LSTM showed higher errors, especially during autumn and winter due to increased meteorological variability. The strong performance of CNN-LSTM is attributed to its efficient spatial feature extraction and ability to capture medium-term temporal dependencies. Overall, the CNN-LSTM model provides a reliable and practical forecasting tool for real-time power prediction and grid applications under varying climatic conditions.

  • Day-ahead Photovoltaic Power Production Forecasting Using a Hybrid Artificial Neural Network Model Integrated with Metaheuristic Algorithms

    by Oguz Tasdemir, Mehmet Yesilbudak, Erdal Irmak

    The escalating global energy demands and the environmental repercussions of fossil fuel utilization have given rise to a marked increase in the level of interest in renewable energy sources. Solar energy, in particular, is distinguished by its abundance and minimal environmental impact. This study sets out to compare three distinct hybrid models that are designed to enhance the forecasting accuracy of daily photovoltaic power prediction: JAYA-ANN, GA-ANN and PSO-ANN. The models were developed and tested using historical data on PV power output, including air temperature, PM10 levels, and solar irradiance. The study's findings indicated that the JAYA-ANN hybrid model exhibited superior performance, with a Mean Absolute Percentage Error (MAPE) of 7.38% and a Root Mean Squared Error (RMSE) of 681.71 kW for the test subset. The JAYA-ANN model demonstrated superior performance in comparison to both GA-ANN and PSO-ANN models. On the basis of the entire dataset, the JAYA-ANN model exhibited the highest level of prediction accuracy, with an MAPE of 11.59% and an RMSE of 413.91 kW. The study confirms that the JAYA-ANN hybrid model serves as an effective tool for photovoltaic power estimation. Beyond this, it offers noteworthy opportunities to advance the integration of solar resources into the energy sector while maintaining grid stability through enhanced forecasting accuracy.


  • Slime Mold Algorithm Approach for Load Flow Analysis and Optimization in Power Systems

    by Oğuz Taşdemir, Salih Ermiş, Abdülkadir Özdoğan

    Electric energy is one of the most commonly used energy sources today. Therefore, how energy can be produced, transmitted, and consumed at the lowest cost is among the main topics that researchers are intensely working on. The limited nature of current energy sources and the rapidly increasing demand for energy necessitate scientific and technological efforts in this field. With a growing world economy and the continuous development and expansion of modern power systems, the voltage problems arising in power systems have become quite significant in terms of controlling energy systems. In this context, one of the most important issues that need to be addressed in power systems is optimal power flow (OPF). Therefore, in the study conducted, the Slime Mold Algorithm (SMA) was used to solve the OPF problem in power systems according to the objective functions, and it was tested with different objective functions. As the objective function, three single objectives (fuel cost, active power loss, and voltage deviation minimization) and the combination of these objective functions, three multi-objective functions, have been determined. The tests conducted to solve the OPF problem were carried out on the IEEE-30 bus system. According to the results obtained, it has been observed that the SMA algorithm is more successful than other algorithms in the literature in solving problems in power systems.

  • Open Access

    An Enhanced Hybrid TLBO–ANN Framework for Accurate Photovoltaic Power Prediction Under Varying Environmental Conditions

    by Salih Ermiş, Oğuz Taşdemir

    This study presents an enhanced hybrid TLBO–ANN model for daily photovoltaic (PV) power generation prediction. By combining the strong nonlinear modeling capacity of Artificial Neural Networks (ANN) with the robust optimization capability of the Teaching–Learning-Based Optimization (TLBO) algorithm, the proposed framework effectively improves prediction accuracy and generalization performance. The model was trained using real meteorological and power generation data and validated on a grid-connected PV power plant in Türkiye. Results indicate that the hybrid TLBO–ANN approach outperforms the conventional ANN by achieving 39.97% and 37.46% improvements on the test subset and overall dataset, respectively. The improved convergence behavior and avoidance of local minima by TLBO contribute to this enhanced accuracy. Overall, the proposed hybrid model provides a powerful and practical tool for reliable PV power forecasting, which can facilitate better grid integration, operational planning, and energy management in renewable energy systems.


  • Open Access

    KIRŞEHİR’İN RÜZGAR ENERJİSİ POTANSİYELİ VE İÇ ANADOLU BÖLGESİ KURULU RÜZGAR ENERJİSİ SANTRALLERİNİN GÜÇ ANALİZİ

    by Müjdat Öztürk, Ramazan Kayabaşı, Oğuz Taşdemir

    Türkiye’nin zengin ve çeşitlilik içeren yenilenebilir enerji potansiyeli, son yıllarda hızla değerlendirilmeye başlanmıştır. Özellikle rüzgar enerjisi, elektrik üretiminde önemli bir rol oynamakta ve kurulu güç içerisindeki payını sürekli artırmaktadır. Çevre dostu bir enerji kaynağı olan rüzgar enerjisi, kırsal bölgelerde de yüksek üretim kapasitesine sahiptir. Bu çalışmada, İç Anadolu Bölgesi illerinin rüzgar potansiyeli ve kurulu santral kapasiteleri; nüfus ve gelişmişlik düzeyleriyle ilişkilendirilerek incelenmiştir. Özel olarak Kırşehir bölgesi ele alınmış ve 2024-2028 yılları arasında bölgedeki rüzgar enerjisi üretim kapasitesi Yapay Sinir Ağları (YSA) tabanlı bir model ile tahmin edilmiştir. Analiz sonuçlarına göre, 2024 yılında rüzgar potansiyelinde yaklaşık %1’lik bir düşüş yaşanması öngörülmüş, ancak 2025-2028 yılları arasında her yıl %1’lik bir artış kaydedilmiştir. 2023 yılındaki üretime kıyasla, 2026 yılında tahmini enerji üretimi %3,5 oranında artış göstermiştir. Aynı şekilde, 2027 ve 2028 yıllarında da enerji üretiminde yükseliş devam etmiştir. Çalışma, İç Anadolu Bölgesi’nin rüzgar enerji potansiyelini detaylı bir şekilde değerlendirirken, Kırşehir ilinde yer alan rüzgar santrali özelinde 2024-2028 yılları arasındaki enerji üretim tahminini ortaya koymuştur. Sonuç olarak, bölgenin mevcut kapasitesi ile potansiyel enerji üretimi ve yıllara göre değişimi kapsamlı bir şekilde analiz edilmiştir.


  • Open Access

    Photovoltaic Power Prediction with Teaching Learning Based Optimization Algorithm

    by Oğuz Taşdemir

    The need for electrical energy has increased considerably due to technological developments. Reducing costs and losses, especially in the supply of electrical energy, is among the goals of energy companies. Photovoltaic energy has been an important alternative in reducing energy costs. However, there are significant power quality problems in transferring the generated photovoltaic energy to the grid. Therefore, the generated photovoltaic energy needs to be accurately estimated to be transferred to the grid smoothly. In the literature, many forecasting models have been used for photovoltaic power forecasting. Each of these forecasting models has estimated photovoltaic power using different input parameters, different estimation intervals, and different estimation algorithms. This paper was conducted using the Teaching-Learning Based Optimization (TLBO) algorithm as an alternative approach to photovoltaic power forecasting models. According to the forecasting results, the root mean square error (RMSE) for the test subset was obtained as 270.32 kW, and the mean absolute percentage error (MAPE) was found to be 3.87%. These results indicate that the TLBO algorithm demonstrates high accuracy for photovoltaic power forecasting and provides an effective alternative model in this field.