Mehmet Bilgili

Estimation of global solar radiation using ANN over Turkey

The main objective of the present study is to develop an artificial neural network (ANN) model based on multi-nonlinear regression (MNLR) method for estimating the monthly mean daily sum global solar radiation at any place of Turkey. For this purpose, the meteorological data of 31 stations spread over Turkey along the years 2000-2006 were used as training (27 stations) and testing (4 stations) data. Firstly, all independent variables (latitude, longitude, altitude, month, monthly minimum atmospheric temperature, maximum atmospheric temperature, mean atmospheric temperature, soil temperature, relative humidity, wind speed, rainfall, atmospheric pressure, vapor pressure, cloudiness and sunshine duration) were added to the Enter regression model. Then, the Stepwise MNLR method was applied to determine the most suitable independent (input) variables. With the use of these input variables, the results obtained by the ANN model were compared with the actual data, and error values were found within acceptable limits. The mean absolute percentage error (MAPE) was found to be 5.34% and correlation coefficient (R) value was obtained to be about 0.9936 for the testing data set.

Wind Characteristics and Energy Potential in Belen-Hatay, Turkey

In this study, wind characteristics in the Belen-Hatay province situated in southern Turkey were investigated by using the Wind Atlas Analysis and Application Program (WAsP) for future wind power generation projects. Hourly wind speeds and directions between the years 2004 and 2005 were collected by the General Directorate of Electrical Power Resources Survey Administration (EIEI). Before the construction of the wind turbine generator in Belen-Hatay province, several fundamental properties of the site such as wind behavior, availability, continuity, and probability were carried out in order to provide the necessary information to the potential investors about cost and economical aspects of the planning wind energy project. The dominant wind directions, probability distributions, Weibull parameters, mean wind speeds, and power potentials were determined according to the wind directions, years, seasons, months, and hours of day, separately. Finally, at a 10 m height above ground level, mean wind speed and power potential of the site were found to be 7.0 m/s and 378 W/m2, respectively.

Prediction of long-term monthly temperature and rainfall in Turkey.

Abstract In this study, artificial neural networks were applied to predict the long-term monthly temperature and rainfall at any target point of Turkey based on the use of the neighboring measuring stations data. For this purpose, meteorological data measured by the Turkish State Meteorological Service between the years 1975 and 2006 from 76 measuring stations were used as training (59 stations) and testing (17 stations) data. Four neurons which receive input signals of latitude, longitude, altitude, and month were used in the input layer of the network. Two neurons, which produce corresponding output signals of the long-term monthly temperature and rainfall, were utilized in the output layer of the network. Finally, the values determined by the artificial neural network model were compared with the actual data. Errors obtained in this model are well within acceptable limits.

Wind Speed Prediction of Target Station from Reference Stations Data

The aim of the present study is to apply an artificial neural network method for daily, weekly, and monthly wind speed predictions in some parts of the Aegean and Marmara region of Turkey that demonstrate acceptable cross-correlations. The wind data taken with an interval of one hour were measured by the General Directorate of Electrical Power Resources Survey Administration at four different measuring stations, namely, Gökçeada, Foca, Gelibolu, and Bababurnu. The wind speeds of three different stations were used as input neurons, while the wind speed of the target station was used as an output neuron in the artificial neural network architecture. The results obtained with this model were compared with the measured data. Errors obtained in this model are within acceptable limits. Results show that the artificial neural network method can successfully predict the daily, weekly, and monthly wind speed of any target station using the measured data of surrounding stations.

Estimation of relative humidity based on artificial neural network approach in the Aegean Region of Turkey

The aim of this study is to estimate the monthly mean relative humidity (MRH) values in the Aegean Region of Turkey with the help of the topographical and meteorological parameters based on artificial neural network (ANN) approach. The monthly MRH values were calculated from the measurement in the meteorological observing stations established in Izmir, Mugla, Aydin, Denizli, Usak, Manisa, Kutahya and Afyonkarahisar provinces between 2000 and 2006. Latitude, longitude, altitude, precipitation and months of the year were used in the input layer of the ANN network, while the MRH was used in output layer of the network. The ANN model was developed using MATLAB software, and then actual values were compared with those obtained by ANN and multi-linear regression methods. It seemed that the obtained values were in the acceptable error limits. It is concluded that the determination of relative humidity values is possible at any target point of the region where the measurement cannot be performed.

Statistical Analysis of Wind Energy Density in the Western Region of Turkey

Abstract In this study, wind energy density in the western region of Turkey was investigated by using the Weibull and Rayleigh probability density functions, and the Wind Atlas Analysis and Application Program. The hourly wind speeds and directions collected by the General Directorate of Electrical Power Resources Survey Administration were used. The dominant wind direction, probability distribution, Weibull parameters, mean wind speed and power potential of all stations were determined by the Weibull and Rayleigh model, and the Wind Atlas Analysis and Application Program. The results obtained with these models were compared with the measured data. Finally, it was found that these regions have a reasonable wind power potential and they are suitable for the plantation of wind energy turbines, but Gökçeada and Gelibolu are the most promising and convenient sites for the production of the electricity from the wind power.

Estimation of human heat loss in five Mediterranean regions

This study investigates the effects of seasonal weather differences on the human bodys heat losses in the Mediterranean region of Turkey. The provinces of Adana, Antakya, Osmaniye, Mersin and Antalya were chosen for the research, and monthly atmospheric temperatures, relative humidity, wind speed and atmospheric pressure data from 2007 were used. In all these provinces, radiative, convective and evaporative heat losses from the human body based on skin surface and respiration were analyzed from meteorological data by using the heat balance equation. According to the results, the rate of radiative, convective and evaporative heat losses from the human body varies considerably from season to season. In all the provinces, 90% of heat loss was caused by heat transfer from the skin, with the remaining 10% taking place through respiration. Furthermore, radiative and convective heat loss through the skin reached the highest values in the winter months at approximately between 110 and 140W/m(2), with the lowest values coming in the summer months at roughly 30-50W/m(2).

Analysis of alumina/water nanofluid in thermally developing region of a circular tube

Analysis of Al2O3/water nanofluid flow in thermally developing region of a circular tube is the subject of present numerical study. In order to consider the hydrodynamically fully developed condition in the tube, a fully developed velocity profile is defined in the inlet section of tube. Three-dimensional computations are performed for a wide variety of nanoparticle concentrations (1 ≤ γ ≤ 10%). On the other hand, for examination of nanoparticle size, effects on the thermal characteristics, two different particle sizes of dp = 25 and 75 nm are applied. The resulting governing equations are solved numerically by means of the finite volume method. For enhanced visualization, different results are presented in thermally developing region. It is obtained that suspending the Al2O3 nanoparticles in pure water increases the thermal boundary layer growing rate. In addition, an increase on the heat transfer rate is observed in thermal boundary layer using the Al2O3 nanoparticles in which this enhancement varies as a function of nanoparticle size and nanoparticle volume concentration. However, it is found that the role of nanoparticle volume concentration on the thermal characteristics such as thermal boundary layer growing rate, temperature gradient, and heat transfer enhancement is significantly important comparing to the nanoparticle size.

Investigation of wind power density at different heights in the Gelibolu peninsula of Turkey

ABSTRACT This study aims to determine the wind characteristics and wind power potential of the Gelibolu peninsula in the Çanakkale region of Turkey. For this purpose, hourly average wind data observed at the Gelibolu meteorological station were used. The Weibull probability density functions and Weibull parameters of time-series of wind speed, mean wind speed, and mean wind power potential were determined for different heights as 10, 20, 30, 40, and 50 m. According to the results obtained at 10- and 50-m heights above the ground level, the annual wind speed varied from 6.85 to 8.58 m/s in this region, respectively. The annual wind power potential of the site was determined as 407 and 800 W/m2 for 10- and 50-m heights, respectively. These results indicate that the investigated site has a reasonable wind power potential for generating electricity.

Modelling of wind turbine power output by using ANNs and ANFIS techniques

In this study, artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS) were applied to estimate the wind turbine power output of a horizontal axis wind turbine. Hub-height wind speed, atmospheric air temperature and rotational speed values obtained from an operating wind power plant (WPP) were employed as input data in the model. According to the derived results, the mean absolute percentage error (MAPE) and correlation coefficient (R) values for the ANN model were determined as 4.41% and 0.9850, respectively, whereas the corresponding values for the ANFIS model were found as 2.19% and 0.9971, respectively. The obtained results showed that ANN and ANFIS models can be used to predict wind turbine power output in a simple, reliable and accurate way.