Sürdürülebilir Kalkınma Amaçları

• 3
• 3
• 2
• 1
• 1

• MakaleAçık Erişim2025Scopus SJRQ2/r/munzur/1927
  Forecasting daily natural gas consumption with regression, time series and machine learning based methods

  Yucesan, Melih; Pekel, Engin; Celik, Erkan; Gul, Muhammet; Serin, Faruk

  An effective short-term natural gas forecasting method contributes to social contributions and allows industrial chain elements to function effectively and minimize economic losses. We dealt with a comparative framework on the applicability of different methods in daily natural gas service (NGS) consumption forecasting. In this context, time series, machine learning, evolutionary and population-based approaches, and their hybrid versions are applied to the NGS data. Hybridized approaches are tested in the scope of NGS consumption forecasting for the first time in the literature in this study. The case of Turkey is handled, and its NGS data is used to demonstrate the comparative framework’s applicability. The comparative study is assessed in the lights of common forecasting accuracy measures of mean absolute percentage error (MAPE), R-squared (R2), and mean squared error (MSE). According to each method’s results, the seasonal autoregressive integrated moving average with exogenous regressors (SARIMAX) and artificial neural network (ANN) hybrid model provides the most dominant performance with respect to MAPE. The lowest error was obtained with a MAPE value of 0.357 in this hybrid model constructed under seven neurons in its ANN structure. This model is followed by another hybrid model, autoregressive integrated moving average (ARIMA)-ANN, with a MAPE value of 0.5 under nine neurons in terms of accuracy performance. The worst performance value belongs to the Genetic algorithm-ANN hybrid model with a MAPE value of approximately 26%.

  • 
  • 
  AtıfScopus16·WoS19·OpenAlex22

  İncele
• MakaleYalnız künye2022Scopus SJRQ2/r/munzur/2764
  Linear programming with fuzzy parameters for inventory routing problem in effective management of personal protective equipment: a case study of corona virus disease 2019

  Göçmen, Elifcan

  Coronavirus disease 2019 (COVID-19) brings about severe disruptions for human living, economics, and environmental balance. This pandemic has boosted the demand for personal protective equipment (PPE) and thus, medical wastes. Thus, a research hypothesis is stated whether it would be possible to provide more efficient distribution and inventory planning to optimize the PPE availability in a fuzzy environment. To confirm the hypothesis, in addition to addressing a scientific novelty considering integration of linear programming with fuzzy parameters, named as the Jimenez’s method and clustering heuristic methods, the practicality of these approaches is provided on a real case study and generated instances from Turkey. The computational results reveal that clustering the 32% of the hospitals ensures optimum total cost and solution time while feasibility degree changes between 0, 4, and 1 values of the Jimenez are not more effective on the results. Improved cost results reveal the economic importance of the healthcare supply chain management and optimal PPE distribution and inventory planning can break down the disease propagation and reduce the detrimental impacts on human life. The proposed approach, for the first time, ensures practical and theoretical insights of distribution and storage decisions across disciplines, namely, engineering and health-care organization authorities.

  • 
  • 
  • 
  AtıfScopus19·WoS12·OpenAlex19

  İncele
• MakaleYalnız künye2022Scopus SJRQ2/r/munzur/2457
  A mathematical programming model for facility location optimization of hydrogen production from renewable energy sources

  Derse, Onur; Göçmen, Elifcan; Yılmaz, Ebru; Erol, Rızvan

  Fossil fuels are the primary energy sources and meet the global energy demands. However, environmental and health problems related with these sources boosted the demand for renewable energy sources. Hydrogen, as an energy carrier has a growing potential for solving these problems. In this article, a mathematical programming model that integrates the production, storage and transportation, safety, location, and staff assignment decisions is presented considering minimization of costs. Although most of the studies focus on location, distribution, storage decisions of hydrogen energy networks, the article also includes production, safety and staff assignment decisions to make this problem more practical. Furthermore, we also investigate the set covering constraint will ensure that each region is covered by minimum number of the hydrogen facilities. The developed model ensures a balance between location, distribution, storage, production, safety and staff decisions by installing two production facilities by assigning total 9 warehouses, 22 tank trucks, 12100 km pipeline, 35 staffs under distance constraint 2000 km in regions 1 and 5. The computational results indicate that the proposed model produces effective solutions for the coverage to all region and minimum total cost for real-case situations.

  • 
  • 
  • 
  AtıfScopus20·WoS16·OpenAlex29

  İncele
• MakaleYalnız künye2020Scopus SJRQ2/r/munzur/3801
  Empirical modeling between degree days and optimum insulation thickness for external wall

  Kallioğlu, Mehmet Ali; Ercan, Umut; Avcı, Ali Serkan; Fidan, Cihad; Karakaya, Hakan

  Insulating is the most effective method that is used to save energy in buildings. Samples from cities from different climatic zones from TS 825 (Turkey) first. Optimum insulation thickness (xopt) analysis is based on two types of insulating and four different fuels (natural gas, coal, fuel oil and electric) of related cities. Cost accounts, payback period and CO2-SO2 emission calculations were performed based on these analyses. Second of all, the relationship between a number of degree day (NDD) and optimum insulation thickness (xopt) was developed by linear, quadratic and cubic correlations. Thirty different mathematical correlations based on different fuel types by using XPS and EPS insulating materials. Twenty-four of these models that were developed were generated peculiar to the fuel type; six of them were generated based on average insulation thickness. R2 values of related correlations are between 0.9989 most and 0.9952 at least as well as it is pretty close to (R ≤ 1) one value. The model among these models is the xopt xopt = a+b (NDD) + c(NDD)2+ d(NDD)3 cubic mathematical model that gives the best average value. a = 0.0036, b = 5E-05, c =–7E-09 and d = 6E-13 are the values for XPS material. Following values are for EPS material; a = 0.0028, b = 5E-13, c =–7E-09 and d = 4E-05. R2 determination coefficient of both two equations is pretty close to 0.9989 and 1; the models obtained are less-than-stellar. Optimum insulation thickness of the area can be known based on the type of material via the number of degree day without the need for long analyses. According to the R2 values, the use of all models is recommended for academic and industrial users.

  • 
  • 
  AtıfScopus21·WoS24·OpenAlex22

  İncele