Yazar "Cetinkaya, Nurettin" seçeneğine göre listele
Listeleniyor 1 - 11 / 11
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Comparison of CO2 Emissions Fossil Fuel Based Energy Generation Plants and Plants with Renewable Energy Source(IEEE, 2014) Uney, Mehmet Sefik; Cetinkaya, NurettinWorld has a rapid growing energy, especially electricity demand parallel with increasing population and developing industry. As a result of increase in electricity demand, electricity generation and associated CO2 and C emissions are also increasing rapidly. Additionally, the consumed amount of energy indicates the development level of countries. For the reduction amount of CO2 and C emissions has been written a lot of article. In this study, for house necessary electrical equipment has collected where in a scenario. The annual need requirement energy detected for this house. According to this scenario, from six different power generation plants were measured CO2 emissions. And comparatively CO2 emissions were evaluated. The aim of this study, fossil energy sources is to show hazards on the environment and in the production of energy is to raise the awareness of people.Öğe Comparison of complex-valued neural network and fuzzy clustering complex-valued neural network for load-flow analysis(SPRINGER-VERLAG BERLIN, 2006) Ceylan, Murat; Cetinkaya, Nurettin; Ceylan, Rahime; Ozbay, YukselNeural networks (NNs) have been widely used in the power industry for applications such as fault classification, protection, fault diagnosis, relaying schemes, load forecasting, power generation and optimal power flow etc. Most of NNs are built upon the environment of real numbers. However, it is well known that in computations related to electric power systems, such as load-flow analysis and fault level estimation etc., complex numbers are extensively involved. The reactive power drawn from a substation, the impedance, busbar voltages and currents are all expressed in complex numbers. Hence, NNs in the complex domain must be adopted for these applications. This paper proposes the complexvalued neural network (CVNN) and a new fuzzy clustering complex-valued neural network (FC-CVNN) to estimate busbar voltages in a load-flow problem. The aim of this paper is to present a comparative study of estimation busbar voltages in load-flow analysis using the conventional neural network (real-valued neural network, RVNN), the CVNN and the new FC-CVNN. The results suggest that a new proposed FC-CVNN and CVNN architecture can generalize better than ordinary RVNN and the FC-CVNN is also learn faster.Öğe Effect of Neutral Grounding Protection Methods for Compensated Wind/PV Grid-Connected Hybrid Power Systems(HINDAWI LTD, 2017) Cetinkaya, Nurettin; Umer, FarhanaThe effects of the wind/PV grid-connected system (GCS) can be categorized as technical, environmental, and economic impacts. It has a vital impact for improving the voltage in the power systems; however, it has some negative effects such as interfacing and fault clearing. This paper discusses different grounding methods for fault protection of High-voltage (HV) power systems. Influences of these grounding methods for various fault characteristics on wind/PV GCSs are discussed. Simulation models are implemented in the Alternative Transient Program (ATP) version of the Electromagnetic Transient Program (EMTP). The models allow for different fault factors and grounding methods. Results are obtained to evaluate the impact of each grounding method on the 3-phase short-circuit fault (SCF), double-line-to-ground (DLG) fault, and single-line-to-ground (SLG) fault features. Solid, resistance, and Petersen coil grounding are compared for different faults on wind/PV GCSs. Transient overcurrent and overvoltage waveforms are used to describe the fault case. This paper is intended as a guide to engineers in selecting adequate grounding and ground fault protection schemes for HV, for evaluating existing wind/PV GCSs to minimize the damage of the system components from faults. This research presents the contribution of wind/PV generators and their comparison with the conventional system alone.Öğe Importance of Holidays for Short Term Load Forecasting Using Adaptive Neural Fuzzy Inference System(Trans Tech Publications Ltd, 2012) Akdemir, Bayram; Cetinkaya, NurettinIn distributing systems, load forecasting is one of the major management problems to carry on energy flowing; protect the systems, and economic management. In order to manage the system, next step of the load characteristics must be inform from historical data sets. For the forecasting, not only historical parameters are used but also external parameters such as weather conditions, seasons and populations and etc. have much importance to forecast the next behavior of the load characteristic. Holidays and week days have different affects on energy consumption in any country. In this study, target is to forecast the peak energy level the next an hour and to compare affects of week days and holidays on peak energy needs. Energy consumption data sets have nonlinear characteristics and it is not easy to fit any curve due to its nonlinearity and lots of parameters. In order to forecast peak energy level, Adaptive neural fuzzy inference system is used for hourly affects of holidays and week days on peak energy level is argued. The obtained values from output of the artificial intelligence are evaluated two fold cross validation and mean absolute percentage error. The obtained two fold cross validation error as mean absolute percentage error is 3.51 and included holidays data set has more accuracy than the data set without holiday. Total success increased 2.4%.Öğe An Improved Particle Swarm Optimization Algorithm Using Eagle Strategy for Power Loss Minimization(HINDAWI LTD, 2017) Yapici, Hamza; Cetinkaya, NurettinThe power loss in electrical power systems is an important issue. Many techniques are used to reduce active power losses in a power system where the controlling of reactive power is one of the methods for decreasing the losses in any power system. In this paper, an improved particle swarm optimization algorithm using eagle strategy (ESPSO) is proposed for solving reactive power optimization problem to minimize the power losses. All simulations and numerical analysis have been performed on IEEE 30-bus power system, IEEE 118-bus power system, and a real power distribution subsystem. Moreover, the proposed method is tested on some benchmark functions. Results obtained in this study are compared with commonly used algorithms: particle swarm optimization (PSO) algorithm, genetic algorithm (GA), artificial bee colony (ABC) algorithm, firefly algorithm (FA), differential evolution (DE), and hybrid genetic algorithm with particle swarm optimization (hGAPSO). Results obtained in all simulations and analysis show that the proposed method is superior and more effective compared to the other methods.Öğe Long-term Electrical Load Forecasting based on Economic and Demographic Data for Turkey(IEEE, 2013) Cetinkaya, NurettinLoad forecasting is very important to operate the electric power systems. One of the primary tasks of an electric utility accurately predicts load demand requirements at all times, especially for long-term. Long term load forecasting (LTLF) is in need to plan and carry on future energy demand and investment such as size of energy plant. LTLF is affected by energy consumption data, national incoming, urbanization rate, population increasing rate and as well as other economic parameters. Artificial Neural Network (ANN) and Artificial Neural Fuzzy Inference System (ANFIS) are the famous artificial intelligence methods and have widely used to solve forecasting problems in literature. In this study, artificial intelligence methods and mathematical modeling (MM) are used to forecast long term energy consumption and peak load for Turkey. The four different input data are used to obtain two different outputs in all three methods. Using the four different variables especially in mathematical modeling has been a novelty for Turkey case study. The results obtained from ANFIS, ANN and MM are compared to show availability. In order to show error levels mean absolute percentage error (MAPE) and mean absolute error (MAE) are used.Öğe Mathematical Programming Based Short Term Load Forecasting Algorithm, Case Study: Turkey 2010(Trans Tech Publications Ltd, 2012) Cetinkaya, NurettinShort-term load forecasting (STLF) is an important problem in the operation of electrical power generation and transmission. In this paper, STLF algorithm was developed for electrical power systems using,mathematical programming with Matlab. A fast and efficient computational algorithm has been obtained for STLF. The mean absolute percentage errors (MAPE) of daily loads forecast and weekly loads forecast for Turkey are found as 1,76%, 1,92%, respectively.Öğe Maximum Power Point Creator Collocating Solar Power Cells for Skewed Surface(IEEE, 2016) Akdemir, Bayram; Cetinkaya, NurettinSolar power is spreading all over the world due to energy policy. Increasing pollution and energy price force to improve solar energy rate in total energy. On the contrary, solar power has some drawbacks. Environmental conditions such as dust, shadow and heat directly affect the solar power cell capability. Especially shadow is one of the biggest problem may can cause broken the cell increasing internal heating of cell under load. Moreover, in case of the shadow position or angle any leg of solar power may collapse and other side of leg force the collapsed side to broke via reverse current flows. Generally, maximum power point tracking method is based on reducing power flows related to generated solar power and only could be adjusted current flows regarding instant cell capability. In this study, a hardware organization was created by microcontroller to obtain maximum power ability. Grouped all cells could be connected each other's. Created groups are paralleled to increase current capability.Öğe A New Mathematical Approach and Heuristic Methods for Load Forecasting in Smart Grid(IEEE, 2016) Cetinkaya, NurettinThis paper presents different methods to solve short-term load forecasting problem in smart grids. Smart grid, an electrical network can be monitored and managed. Effective and efficient use of energy and a low-cost planning-oriented management are required in smart grids. One of the most important helpers for power management is to forecast load correctly. Load forecasting, demand response and energy prices affect each other. At the same time the load forecasting has an important role for safely operating conditions and power systems control. In this study, the effects of load forecasting in a real network operating conditions are examined. Also a time series mathematical model and heuristic models have been developed for load forecasting. Performances of the forecasting of the models developed were compared with the actual values.Öğe Reduction of Power Loss Using Reactive Power Optimization in a Real Distribution System(IEEE, 2015) Yapici, Hamza; Cetinkaya, NurettinElectrical power losses are an important factor for the operation of power systems. Reactive power optimization can reduce power loss. This paper describes the solution of reactive power optimization problem using particle swarm optimization and genetic algorithm. The numerical analysis has been carried out in a part of real power system in Turkey that is managed by MEDA. The goal of this study is minimizing the active power loss of the whole distribution network. Due to the absence of any generators in the distribution network, shunt capacitors and bus voltages are taken as control variables. The values of control variables are determined by the both algorithms and the results are compared.Öğe Wind Power Estimation Algorithm Using Artificial Neural Networks Case Study: Eregli(IEEE, 2014) Cetinkaya, Nurettin; Yapici, HamzaBy the global warming and decreasing fossil fuel, alternative energy sources are looked for future and protecting environment. In the recent years, many studies are made about wind power whereby deteriorating environment will be regarded. This study prefers artificial neural network (ANN) algorithm to estimate electrical energy output of wind turbines can be constructed. Although many environmental effects such as wind speed, air density or temperature influence wind turbines installation, ANN estimates electrical energy and power output in the minimum cost. The wind turbine parameters of three manufacturers have been chosen so as to train ANN. For the structure of ANN, 1 hidden layer and 26 neurons have been set. Data in this work have been measured at Eregli terrain in Konya, Turkey. This daily data have been taken between January 2013 and February 2014.
