2026-10-29T22:55:57Zhttps://munzur-rdlopen.rawdatalibrary.net/oai/request

oai:munzur-rdlopen.rawdatalibrary.net:munzur/53622026-10-28T15:07:11Zopenairecom_munzur_1col_munzur_2

Estimating Global Solar Radiation for Tunceli City using ANFISCelik, ErkanGul, MuhammetBilgisayar Bilimleri, Yazılım MühendisliğiBecause of the high cost of measurement equipment and their maintenance, global solar radiation measurement is not always implemented. Hence, several forecasting approaches based on fuzzy sets, artificial intelligence or soft computing are proposed to forecast global solar radiation owing to being less cost. However, it is vital to select the most suitable approach for a specific purpose and region. In this study, the adaptive-network based fuzzy inference systems (ANFIS) is proposed to forecast monthly mean daily global solar radiation for Tunceli, Turkey. The monthly data between 1990 and 2010 is used for the proposed approach. The data was obtained from provincial directorate of meteorology of Tunceli. According to the gathered data, the highest value of monthly average daily global solar radiation was measured as 5.218 kWh/m² in the year of 1993. The lowest one with a value of 3.905 kWh/m² belongs to the year of 1997. Similarly, the highest value of monthly average daily sunshine duration was measured as 8.71 hours in the year of 1993. The lowest one with a value of 6.64 hours belongs to the year of 2009. When the data is analysed on a monthly basis, the highest value of monthly average daily global solar radiation was measured as 7.409 kWh/m² in the month of June. The lowest one with a value of 1.762 kWh/m² belongs to the month of December. Similarly, the highest value of monthly average daily sunshine duration was measured as 12 hours in the month of July. The lowest one with a value of 3.1 hours belongs to the month of December. The experiments were applied in MATLAB 7 package software in order to obtain the optimum network architecture. In this network, there are 3 inputs (months, years and monthly average daily sunshine duration) and 1 output (the estimation of the monthly average daily global solar radiation). The ANFIS proposed in this study has Gaussian membership function and twenty fuzzy rules are used. The number of the data points (monthly average daily global solar radiation measurement) is 245. As a performance measure of the ANFIS network, the mean absolute percentage error (MAPE) was used. In testing stage, the MAPE was obtained as 6.365 which is quite well for this type of problem. The coefficient of determination (RSquared) value was calculated as 0.999 which is significantly high. The highly successful results show the success of the fuzzy based methodology of ANFIS which provides estimations of global solar radiation successfully. The presented approach shows that the ANFIS illustrates promising in the forecasting of monthly mean daily global solar radiation using available data. Future studies to estimate the monthly mean global solar radiation of Tunceli city with greater accuracy can be achieved using more apparent meteorological input parameters and different artificial intelligence techniques like artificial neural networks, autoregressive moving average methods or support vector machines. These methods can be improved for available models of daily and hourly estimation of global solar radiation.2017Articlehttps://rdlopen.rawdatalibrary.net/r/munzur/53621309-8640trDicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisiinfo:eu-repo/semantics/closedAccessinfo:eu-repo/semantics/articlehttps://munzur-rdlopen.rawdatalibrary.net/tr/items/munzur/5362