Erol Arcaklioğlu

Use of artificial neural networks for mapping of solar potential in Turkey

Turkey has sufficient solar radiation intensities and radiation durations for solar thermal applications since Turkey lies in a sunny belt, between 36° and 42° N latitudes. The yearly average solar-radiation is 3.6 kWh/m2day, and the total yearly radiation period is ~2610 h. The main focus of this study is to determine the solar-energy potential in Turkey using artificial neural-networks (ANNs). Scaled conjugate gradient (SCG), Pola-Ribiere conjugate gradient (CGP), and Levenberg-Marquardt (LM) learning algorithms and a logistic sigmoid transfer function were used in the network. In order to train the neural network, meteorological data for the last 3 years (2000-2002) from 17 stations (namely cities) spread over Turkey were used as training (11 stations) and testing (6 stations) data. Meteorological and geographical data (latitude, longitude, altitude, month, mean sunshine duration, and mean temperature) are used as inputs to the network. Solar radiation is in the output layer. The maximum mean absolute percentage error was found to be less than 6.7% and R2values to be about 99.8937% for the testing stations. However, the respective values were found to be 2.41 and 99.99658% for the training stations. The trained and tested ANN models show greater accuracies for evaluating solar resource posibilities in regions where a network of monitoring stations has not been established in Turkey. The predicted solar-potential values from the ANN were given in the form of monthly maps. These maps are of prime importance for different working disciplines, like those of scientists, architects, meteorologists, and solar engineers in Turkey. The predictions from ANN models could enable scientists to locate and design solar-energy systems in Turkey and determine the appropriate solar technology.

Prospects for Future Projections of the Basic Energy Sources in Turkey

Abstract The main goal of this study is to develop the energy sources estimation equations in order to estimate the future projections and make correct investments in Turkey using artificial neural network (ANN) approach. It is also expected that this study will be helpful in demonstrating energy situation of Turkey in amount of EU countries. Basic energy indicators such as population, gross generation, installed capacity, net energy consumption, import, export are used in input layer of ANN. Basic energy sources such as coal, lignite, fuel-oil, natural gas and hydraulic are in output layer. Data from 1975 to 2003 are used to train. Three years (1981, 1994 and 2003) are only used as test data to confirm this method. Also, in this study, the best approach was investigated for each energy sources by using different learning algorithms (scaled conjugate gradient [SCG] and Levenberg-Marquardt [LM]) and a logistic sigmoid transfer function in the ANN with developed software. The statistical coefficients of multiple determinations (R2-value) for training data are equal to 0.99802, 0.99918, 0.997134, 0.998831 and 0.995681 for natural gas, lignite, coal, hydraulic, and fuel-oil, respectively. Similarly, these values for testing data are equal to 0.995623, 0.999456, 0.998545, 0.999236, and 0.99002. The best approach was found for lignite by SCG algorithm with seven neurons so mean absolute percentage error (MAPE) is equal to 1.646753 for lignite. According to the results, the future projections of energy indicators using ANN technique have been obviously predicted within acceptable errors. Apart from reducing the whole time required, the importance of the ANN approach is possible to find solutions that make energy applications more viable and thus more attractive to potential users.

Forecasting Net Energy Consumption Using Artificial Neural Network

The main goal of this study is to develop the equations for forecasting net energy consumption (NEC) using the artificial neural network (ANN) technique in order to determine the future level of the energy consumption in Turkey. Logistic sigmoid transfer function was used in the network. In order to train the neural network, population, and gross generation, installed capacity and years is used in input layer of network. The net energy consumption is in output layer. The input values in 1965, 1981, and 1997 are only used as test data to confirm this method. The statistical coefficient of multiple determinations (R 2-value) is equal to 0.9999 and 1 for training and test data, respectively. According to the results, the NEC using the ANN technique has been obviously predicted within acceptable errors. Apart from reducing the whole time required, the importance of the ANN approach is possible to find solutions that make energy applications more viable and thus more attractive to potential users. It is also expected that this study will be helpful in developing highly applicable and productive planning for energy policies.

Determination of thermodynamic properties of an alternative refrigerant (R407c) using artificial neural network

Thermodynamic analysis of the refrigeration systems is too complex because of thermodynamic properties equations of working fluids, involving the solution of complex differential equations. To simplify this complex process, this paper proposes a new approach (artificial neural network, ANN) to determine of thermodynamic properties of an environmentally friendly alternative refrigerant (R407c) for both saturated liquid-vapor region (wet vapor) and superheated vapor region. Instead of complex rules and mathematical routines, ANNs are able to learn the key information patterns within multidimensional information domain. Therefore, reducing the risk of experimental uncertainties and also removing the need for complex analytic equations requiring long computational time and efforts. R^2 values - which are errors known as absolute fraction of variance - in wet vapor region are 0.999706, 0.999949, 0.999909, 0.999988 and 0.999836 for specific volume, enthalpy, entropy, viscosity and thermal conductivity for training, respectively. Similarly, for superheated vapor, they are: 0.99992, 1, 0.99998, 0.99995 and 0.99996 for training data, respectively. Promising thermodynamics property results have been obtained for R407c within acceptable errors. PVTx properties predicted are in valid region for working conditions of the refrigeration systems in case of use to computer simulation programs.

Modelling of Turkey's net energy consumption using artificial neural network

The main goal of this study is to develop the equations for forecasting net energy consumption (NEC) using artificial neural network (ANN) technique in order to determine the future level of the energy consumption in Turkey. Two different models were used in order to train the neural network: population, gross generation, installed capacity and years are used in input layer of network (Model 1); energy sources are used in input layer of network (Model 2). The NEC is in output layer for two models. R2 values for training data are equal to 0.99944 and 0.99913, for Model 1 and Model 2, respectively. Similarly, R2 values for testing data are equal to 0.997386 and 0.999558 for Model 1 and Model 2, respectively. According to the results, the NEC prediction using ANN technique will be helpful in developing highly applicable and productive planning for energy policies.

A Study for Estimating Solar Resources in Turkey Using Artificial Neural Networks

Turkey has sufficient solar radiation and radiation period for solar thermal applications since it lies in a sunny belt between 36° and 42° N latitudes. The yearly average solar radiation is 3.6 kWh/m2day, and the total yearly radiation period is ∼2610 h. This study investigates the estimation of solar resources in Turkey using artificial neural networks (ANNs). Scaled conjugate gradient (SCG), Pola-Ribiere conjugate gradient (CGP), and Levenberg-Marquardt (LM) learning algorithms and logistic sigmoid transfer function were used in the network. In order to train the neural network, meteorological data for last three years (2000–2002) from 17 stations (namely cities) spread over Turkey were used as training (11 stations) and testing (6 stations) data. These cities selected can give a general idea about Turkey. Meteorological and geographical data (latitude, longitude, altitude, month, mean sunshine duration, and mean temperature) is used in input layer of network. Solar radiation is in output layer. The maximum mean absolute percentage error was found to be less than 6.7% and R2 values to be about 99.8937% for the testing stations. However, these values were found to be 2.41% and 99.99658% for the training stations. The results indicate that the ANN model seems promising for evaluating solar resource posibilities at the places where there are no monitoring stations in Turkey. The results on the testing stations indicate a relatively good agreement between the observed and the predicted values.

Derivation of empirical equations for thermodynamic properties of a ozone safe refrigerant (R404a) using artificial neural network

This study, deals with the potential application of the artificial neural networks (ANNs) to represent PVTx (pressure-specific volume-temperature-vapor quality) data in the range of temperature of 173-498K and pressure of 10-3600kPa. Generally, numerical equations of thermodynamic properties are used in the computer simulation analysis instead of analytical differential equations. And also analytical computer codes usually require a large amount of computer power and need a considerable amount of time to give accurate predictions. Instead of complex rules and mathematical routines, this study proposes an alternative approach based on ANN to determine the thermodynamic properties of an environmentally friendly refrigerant (R404a) for both saturated liquid-vapor region (wet vapor) and superheated vapor region as numerical equations. Therefore, reducing the risk of experimental uncertainties and also removing the need for complex analytic equations requiring long computational time and effort. R^2 values - which are errors known as absolute fraction of variance - in wet vapor region are 0.999401, 0.999982 and 0.999993 for specific volume, enthalpy and entropy for training data, respectively. For testing data, these values are 0.998808, 0.999988, and 0.999993. Similarly, for superheated vapor region, they are: 0.999967, 0.999999 and 0.999999 for training data, 0.999978, 0.999997 and 0.999999 for testing data. As seen from the results of mathematical modeling, the calculated thermodynamic properties are obviously within acceptable uncertainties.

Estimation of GHG Emissions in Turkey Using Energy and Economic Indicators

Abstract The greenhouse gas emissions (total greenhouse gas, CO2, CO, SO2, NO2, E (emissions of non-methane volatile organic compounds)) covered by the Kyoto Protocol are weighted by their global warming potentials and aggregated to give total emissions in CO2 equivalents. The subject in this study is to obtain equations to predict the greenhouse gas emissions of Turkey using energy and economic indicators by the artificial neural network approach. In this study, three different models were used in order to train the artificial neural network. In the first of them sectoral energy consumption (Model 1), in the second of them gross domestic product (Model 2), and in the third of them gross national product (Model 3) are used input layer of the network. The greenhouse gas emissions are in the output layer for all models. The aim of using different models is to estimate the greenhouse gas emissions with high confidence to make correct investments in Turkey. The obtained equations are used to determine the future level of the greenhouse gas emissions and take measures to control the share of sectors in total emission. According to artificial neural network results, the maximum mean absolute percentage errors for Model 1 were found to be 0.147151, 0.066716, 0.181901, 0.105146, 0.124684, and 0.158157 for greenhouse gas, SO2, NO2, CO, E, and CO2, about training data with Levenberg-Marquardt algorithm by eight neurons, respectively. Similarly, for Model 2 these values were found to be 0.487212, 0.701938, 0.718754, 0.232667, 0.272346, and 0.575421, respectively. And finally, for Model 3, these values were found to be 0.126728, 0.115135, 0.069296, 0.214888, 0.080358, and 0.179481, respectively. R2 values are obtained very close to 1 for all models. The artificial neural network approach shows greater accuracy for estimating the greenhouse gas emissions.

Estimation of Net Energy Consumption in Turkey Using Different Indicators

Abstract The main subject in this study is to obtain equations to predict net energy consumption of Turkey using energy sources and economic indicators by artificial neural network approach in order to determine the future level of the energy consumption and make correct investments in Turkey. In this study, three different models were used in order to train the artificial neural network. In the first model (Model 1), energy sources (e.g., natural gas, lignite, coal, hydraulic); in the second model (Model 2), gross national product; and in the third model (Model 3), gross domestic product, are used for the input layer of the network. The net energy consumption is in the output layer for all models. In order to train the neural network, economic and energy data for the last 37 years (1968–2005) is used in network for all models. The aim of using different models is to estimate the net energy consumption with high confidence to plan for future projections. The maximum mean absolute percentage error was found to be 1.992262, 1.110525, and 1.122048 for Model 1, Model 2, and Model 3, respectively. R2 values are obtained (0.999558, 0.999903, and 0.999903 for training data of Model 1, Model 2, and Model 3, respectively). The artificial neural network approach shows greater accuracy for evaluating net energy consumption based on economic indicators. Also, obtained results in this study were compared with results of similar studies using various techniques.

The Forecasting of Net Electricity Consumption of the Consumer Groups in Turkey

Abstract The main goal of this study is to reveal the future projections of net electricity consumption (NEC) as the consumer groups in Turkey by using the artificial neural network (ANN) technique. In this study the equations based on energy and economic indicators were obtained to predict the net electricity consumption as the consumer groups with high confidence to plan correct investments in Turkey. In this study, three different models were used in order to train the ANN. In Model 1, energy indicators such as installed capacity, generation, energy import and energy export were used as the input layer of the network. In Model 2, the sectoral share of Gross National Product (GNP) per capita was used. In Model 3, the sectoral share of Gross Domestic Product (GDP) per capita was used. The NEC of 25 different consumer groups are in the output layer for all models. The aim of using different models is to demonstrate the effect of sectoral share of economic indicators (GNP and GDP) on the estimation of NEC. R2 values are obtained ~1 for all models as consumer groups. Based on the output of the study, the ANN model can be used to estimate the NEC as the consumer groups from the energy and economic indicators.