BKBayram Köse

Bayram Köse

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bayram Köse has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    EXAMINATION OF THE RED PANDA ALGORITHM FOR SOLVING THE TRAVELING SALESMAN PROBLEM: AN EXAMPLE OF DETERMINING ROUTES TO DISASTER AND EMERGENCY ASSEMBLY AREAS

    by Derya Zariç Kökçü, Şükran Konca, Bayram Köse

    This study analyzes the Red Panda Optimization Algorithm (RPOA), inspired by nature, in solving the Traveling Salesman Problem (TSP). Specifically, it aims to determine the shortest and most efficient routes to assembly areas during disasters. TSP is a fundamental problem with a wide range of applications in logistics, route planning, distribution, and facility location. It is a problem classified as NP-hard (difficult to solve) with a large solution space, and has been studied by researchers for many years. Due to the rapidly growing solution space, solving it with classical methods is impractical. For this problem, where classical methods are insufficient, RPOA, which mimics the feeding and resting behaviors of red pandas, offers an effective search strategy. In this study, the algorithm is tested using the coordinates of 115 real disaster and emergency assembly areas located in Karşıyaka district of İzmir province. The performance of RPOA is compared with the classical randomized TSP algorithm; its solution quality and computation time are analyzed. The results show that RPOA produces shorter routes and, in some cases, reaches a solution faster. These findings demonstrate the algorithm's usability in time-critical applications such as disaster management.

  • ZAMANSAL FÜZYON DÖNÜŞTÜRÜCÜ (TFT) YÖNTEMİYLE YAĞIŞ TAHMİNİ

    by Serkan Ansay, Bayram Köse

    Geçmişten günümüze atmosferde gerçekleşen olaylar olayın gerçekleştiği çevrede tahmin yürütebilmek için araştırma konusu olmaktadır. Bu tahminler, toplanan verilerin sayısal formüllerden geçirilmesiyle oluşan sonuçların değerlendirilmesiyle gerçekleşmektedir. Teknolojinin yazılım ve donanım olarak hızla gelişmesi, literatüre yeni yöntem ve tekniklerin kazandırılmasının temelini oluşturmaktadır. Tahmin aşamasında kullanılan Yapay Sinir Ağları bu yöntemlerden biridir. Bu çalışmada geçmiş toplam küresel güneş radyasyonu, güneşlenme süresi ,rüzgar hızı, bulutluluk miktarı, nem, sıcaklık parametreleri kullanılarak Uzun Kısa Süreli Bellek (LSTM- Long Short-Term Memory) ile Zamansal Füzyon Dönüştürücü (TFT- Temporal Fusion Transformer) yöntemleri karşılaştırılmıştır. Elde edilen sonuçlar, TFT modelinin (RMSE = 0.039, MAE = 0.028, R² = 0.981) performansının, LSTM modeline (RMSE = 0.061, MAE = 0.045, R² = 0.954) göre belirgin biçimde daha yüksek tahmin doğruluğu ve genelleme yeteneği sunduğunu ortaya koymaktadır. Bu üstünlük, TFT’nin çok değişkenli meteorolojik veriler arasındaki zamansal ilişkileri gated residual network yapısı ve çok başlı dikkat (multi-head attention) mekanizması aracılığıyla etkili biçimde yakalayabilmesinden kaynaklanmaktadır; böylece kısa vadeli yağış tahmininde yaklaşık %35 düzeyinde hata azalımı elde edilmiştir.

  • Open Access

    AC Fault Detection in On-Grid Photovoltaic Systems by Machine Learning Techniques

    by Muhammet Tahir Guneser, Sakir Kuzey, Bayram Kose

    The increasing integration of solar energy into the power grid necessitates robust fault detection and diagnosis (FDD) guidelines to ensure energy continuity and optimize the performance of grid-connected photovoltaic (GCPV) systems. This research addresses a gap in the literature by systematically evaluating machine learning (ML) algorithms for the detection and classification of AC-side faults (inverter and grid faults) in GCPV systems. We utilized three commonly employed algorithms, namely K-Nearest Neighbors (KNN), Logistic Regression (LR), and Artificial Neural Networks (ANNs), to develop fault detection models. These models were trained using a monthly electrical dataset obtained from the AYCEM-GES-GCPV power plant in Giresun, Turkiye, and their performance was rigorously evaluated using classification accuracy, Area Under the Curve (AUC), and Receiver Operating Characteristic (ROC) analyses. The results demonstrate that the algorithms are highly effective in fault detection, with AUC values consistently exceeding the critical threshold. The obtained accuracies for KNN, LR, and ANN were 0.9826, 0.782, and 0.7096, respectively. These findings emphasize the high effectiveness of ML algorithms, with KNN exhibiting the best performance, for identifying AC-side faults in GCPV installations. While the study focused on AC-side fault detection, subsequent work developed a smart card module to identify complex DC side electrical faults and built a PV array for experimental testing.


  • Open Access

    Forecasting Wind Speed with Autoregressive and Long-Short Term Memory Neural Network Models

    by Serkan Ansay, Bayram Köse, İbRahim Işıklı, Ceyda Mülayim, Bekir Ertilav

    The growing need for sustainable and efficient energy systems has intensified interest in accurate renewable energy forecasting. In particular, wind speed forecasting is vital for the reliable integration of wind energy into power systems. This study investigates and compares the performance of three different approaches for wind speed prediction: Autoregressive (AR), Long Short-Term Memory (LSTM) neural networks, and a hybrid AR–LSTM model. Real wind speed data collected from İzmir, Turkey, were used in the experiments. The AR model, a linear statistical method, was evaluated alongside the LSTM model, a deep learning method capable of capturing long-term temporal dependencies. A hybrid model was also developed to benefit from the strengths of both. Additionally, noise reduction techniques such as Moving Average and Gaussian Filtering were applied to enhance data quality and model accuracy. The results demonstrated that the LSTM model achieved the lowest RMSE value (0.084), outperforming both the AR and hybrid models. This suggests that LSTM-based models are more suitable for capturing complex and nonlinear patterns in wind speed data. The findings contribute to the development of intelligent forecasting systems for efficient renewable energy management.


  • Open Access

    Weibull Parameter Estimation Using Empirical and AI Methods: A Wind Energy Assessment in İzmir

    by Bayram Köse

    This study evaluates the estimation of Weibull distribution parameters (shape, k; scale, c) for wind speed modeling in wind energy potential assessments. Traditional empirical methods—Justus Moment Method (JEM), Power Density Method (PDM), Energy Pattern Factor Method (EPFM), Lysen Moment Method (LAM), and Standard Deviation Empirical Method (SEM)—are compared with advanced artificial intelligence optimization algorithms (AIOAs), including Genetic Algorithm (GA), Gravitational Search Algorithm (GSA), Sine Cosine Algorithm (SCA), Teaching-Learning-Based Optimization (TLBA), Grey Wolf Optimizer (GWA), Red Fox Algorithm (RFA), and Red Panda Optimization Algorithm (RPA). Using hourly wind speed data from Foça, Urla, Karaburun, and Çeşme in Turkey, the analysis demonstrates that AIOAs, particularly GA, GSA, SCA, TLBA, and GWA, outperform empirical methods, achieving low RMSE (0.0071) and high R2 (0.9755). SEM and LAM perform competitively among empirical methods, while PDM and EPFM show higher errors, highlighting their limitations in complex wind speed distributions. The study also conducts a techno-economic analysis, assessing capacity factors, unit energy costs, and payback periods. Foça and Urla are identified as optimal investment sites due to high energy yields and economic efficiency, whereas Çeşme is unviable due to low production and long payback periods. This research provides a robust framework for Weibull parameter estimation, demonstrating AIOAs’ superior accuracy and offering a decision-support tool for sustainable wind energy investments.


  • Open Access

    Application of Search Algorithms to Root-Finding Problems in Algebraic and Transcendental Contexts

    by Bayram Köse, Bahar Demirturk, Şükran Konca

    In this study, bisection algorithm, golden ratio and Fibonacci search algorithms are used to find the roots of univariate, logarithmic, trigonometric, exponential and polynomial functions. The results obtained from these methods are compared, and the fundamental principles, advantages, and disadvantages of each algorithm are discussed in terms of numerical stability. The approximation to the root with minimal error and the fewest steps is analyzed. The study concludes with results and recommendations based on comparative analysis.


  • Open Access

    Two Approaches For Solving Nonlinear Equation Systems: Newton Raphson and Red Fox

    by Bayram Köse, Bahar Demirtürk, Şükran Konca

    In this study, the results obtained by using the Red Fox method, a new metaheuristic optimization method, and the Newton Raphson method, which is one of the numerical methods, in finding the solutions of nonlinear systems of equations, are compared and these comparative analyses are evaluated and recommendations are presented.


  • Open Access

    Iterative Solutions for Certain Complex Coefficient Linear Systems: Jacobi and Gauss-Seidel Methods

    by Ahmet Zahid Küçük, Bayram Köse, Bahriye Karaca

    In this study, the performance of the Jacobi and Gauss-Seidel iteration methods for solving systems of linear equations with complex coefficients is analyzed. The coefficient matrix of the system is transformed into a real coefficient system by separating the real and imaginary parts. The study aims to compare the accuracy and computational efficiency of these methods within the context of selected examples, while also evaluating their convergence behavior. The findings demonstrate that, for the examples considered, the Gauss-Seidel method converges faster and with lower initial errors compared to the Jacobi method.