Yazar "Kayisli, Korhan" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Energy Management of DC Microgrid-based Photovoltaic/Battery and Super Capacitor
    (Institute of Electrical and Electronics Engineers Inc., 2024) Berboucha, Ali; Aissou, Said; Çolak, İlhami; Djermouni, Kamel; Belkaid, Abdelhakim; Amirouche, Elyazid; Kayisli, Korhan
    The large use of microgrids, particularly direct current microgrids, is a global trend driven by the increasing integration of renewable energy sources with energy storage systems. DC microgrids offer the distinct advantage of eliminating harmonics and synchronization challenges, making them a focal point for research and engineering attentions. Considering the intermittent nature of primary renewable energy sources, such as photovoltaic and wind energy, the integration of energy storage systems is necessary to improve the reliability, stability, and overall performance of microgrids. This paper proposes an isolated DC microgrid including a photovoltaic array, a hybrid storage system based on a supercapacitor and battery bank, power electronic converters and a variable load. An energy management system to optimize operation of an islanded DC microgrid is presented. The EMS effectively regulates the DC bus voltage and balances power flow within system. To support the EMS, the test condition considers Maximum Power Point Tracking for the photovoltaic array, state of charge management for the battery and supercapacitor banks and converter control strategies to maintain DC bus voltage stability. © 2024 IEEE.
  • Küçük Resim Yok
    Öğe
    Predicting LAN switch failures: an integrated approach with DES and machine learning techniques (RF/LR/DT/SVM)
    (Elsevier, 2024) Myrzatay, Ali; Rzayevac, Leila; Bandini, Stefania; Shayea, Ibraheem; Saoud, Bilal; Çolak, İlhami; Kayisli, Korhan
    This research paper introduces an innovative approach to predicting failures in Local Area Network (LAN) switches, combining Double Exponential Smoothing (DES) with a suite of Machine Learning (ML) algorithms including Random Forest (RF), Logistic Regression (LR), Decision Trees (DT), and Support Vector Machines (SVM). The primary objective of this study is to enhance the accuracy and timeliness of LAN switch failure predictions, thereby facilitating more proactive and effective network management. Our methodology involves the integration of DES for trend analysis and forecasting in time -series data, with the advanced predictive capabilities of the aforementioned ML algorithms. This hybrid approach not only leverages the strengths of DES in identifying underlying patterns in failure data but also capitalizes on the diverse predictive models to handle various aspects of failure prediction more robustly. The paper details the process of data collection, preprocessing, and the specific application of DES and each ML algorithm to the dataset. A notable contribution of this research is the development of a framework that effectively combines the output of DES with ML models, leading to a significant improvement in predictive accuracy as compared to traditional methods. Through rigorous testing and validation; the proposed approach demonstrated a marked increase in the precision and reliability of failure predictions. The results indicate that the integration of DES with ML algorithms can substantially aid in preemptive maintenance and decision -making processes in LAN management. The implications of these findings are profound, suggesting that such a combined approach can greatly enhance network stability and efficiency. While the focus of this study is on LAN switches, the methodology has the potential for broader applications in various fields of network management and predictive maintenance.
  • Küçük Resim Yok
    Öğe
    PV-MPPT Lab: A GUI-Based Education Tool for MPPT Techniques
    (Ieee-Inst Electrical Electronics Engineers Inc, 2024) Kayisli, Korhan; Caglayan, Ruhi Zafer; Colak, Ilhami
    This article aims to present the design of a GUI application that serves as an educational and analytical tool. The GUI application is intended for educational purposes, allowing users to learn about the linear and renewable energy sources. This GUI has been designed to explain, teach, and implement maximum power point tracking (MPPT) techniques that enable maximum power extraction from photovoltaic (PV) panels. Contribution: This study introduces a novel educational tool designed to enhance the understanding of different MPPT methods among engineering students. The GUI tool was implemented and utilized throughout a semester in the course named power electronic applications in power systems, specifically aimed at postgraduate level students. Background: Engineering students often encounter challenges in grasping advanced concepts, such as MPPT techniques, which are crucial for optimizing the performance of PV systems. Traditional teaching methods may not fully address the learning needs of students in this complex subject area. Research Question: How does the use of a GUI-based educational tool for MPPT techniques impact the learning outcomes and attitudes of engineering students in a postgraduate course? Methodology: The effectiveness of the GUI was assessed by comparing the performance of students who used this tool with those from the previous year who did not. The study involved a semester-long deployment of the tool in the power electronic applications in power systems course, with participation from students specializing in renewable energy engineering. Findings: Preliminary findings suggest an improvement in the performance of students using the PV-MPPT Lab compared to those from the previous year. The study also indicates positive student attitudes toward the GUI tool, highlighting its potential as an effective learning aid in engineering education.