Search

Technological advancements coupled with growing world population require the increasing need of energy. Natural gas is one of the most important usable energy resources. Turkey is with high external dependency on energy as it has its own limited natural and underground energy resources. Thus, in order to effectively and productively use of natural gas purchased from foreign countries and to make reliable and robust energy policies for the years ahead, it is crucial to make a reasonable and plausible prediction for natural gas consumption of Turkey. In this paper, we estimate the natural gas consumption using machine learning techniques on the basis of real monthly data representing natural gas consumption of Turkey between the years 2010 and 2018. The performances of machine learning techniques involving Artificial Neural Networks, Random Forest Tree, Regression, Time Series and Multiple Seasonality Time Series are compared in predicting the natural gas consumption of Turkey. Experimental results show that among the five techniques, artificial neural networks produce the best estimation, having the lowest mean square errors, followed by regression method. Time series shows the worst performance among all the techniques. [ABSTRACT FROM AUTHOR]

Often, solar irradiation estimation from simply measureable sunshine duration data is achieved by linear and nonlinear regression expressions, which depicts the statistical regression equation between the sunshine duration and solar irradiation data. These models are based on statistical parameters only, and therefore, the estimations do not take into consideration deviations from the averages. In this paper, an innovative probability methodology is proposed for solar irradiation estimation, which is based on the cumulative probability distribution functions (CDFs) of the sunshine duration and solar irradiation data. For this purpose, the sunshine duration data are converted to match the solar irradiation data cumulative distribution (CDF), which is then employed for the solar irradiation estimation. Hence, the CDFs of sunshine duration and solar irradiation data are preserved, and rather than global average, pointwise solar irradiation estimations are achieved. The application of the innovative probabilistic methodology is presented for seven solar irradiation measurements stations from different climate regions in Turkey. It is shown that the suggested method over performs other methodologies with very high improvements. Copyright © 2016 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Abstract: This paper proposes a new hybrid method (HAP) for estimating energy demand of Turkey using Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO). Proposed energy demand model (HAPE) is the first model which integrates two mentioned meta-heuristic techniques. While, PSO, developed for solving continuous optimization problems, is a population based stochastic technique; ACO, simulating behaviors between nest and food source of real ants, is generally used for discrete optimizations. Hybrid method based PSO and ACO is developed to estimate energy demand using gross domestic product (GDP), population, import and export. HAPE is developed in two forms which are linear (HAPEL) and quadratic (HAPEQ). The future energy demand is estimated under different scenarios. In order to show the accuracy of the algorithm, a comparison is made with ACO and PSO which are developed for the same problem. According to obtained results, relative estimation errors of the HAPE model are the lowest of them and quadratic form (HAPEQ) provides better-fit solutions due to fluctuations of the socio-economic indicators. [Copyright &y& Elsevier]

Simple solar irradiation estimation models most often use classical regression analysis with a set of restrictive assumptions. They work with actual measurements on Cartesian coordinate systems, and given the predictor as sunshine duration, the solar irradiation amount is estimated through a regression model. The variances of solar irradiation and sunshine data are not considered explicitly whereas they are physically significant in representing diffusion, absorption and reflection of the solar irradiation depending on the atmospheric composition and weather situation, especially, in terms of cloudiness, which is directly related to sunshine duration during day light. This paper proposes more efficient approach in terms of physical interpretations and mathematical convenience in modeling solar irradiation and sunshine duration relationship. For this purpose, two dimensional principal component analysis is employed and the solar irradiation estimations are found more reliably than the classical approaches. The application of the methodology is presented for five sunshine duration and irradiation record stations in Turkey. [Copyright &y& Elsevier]