Estimation of Measured Global Solar Radiation by Artificial Neural Networks for Mersin / Turkey and Comparison with Common Solar Radiation Models
Journal Title: Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji - Year 2019, Vol 7, Issue 1
Abstract
In this study, the daily total global solar radiation values measured for Mersin between April 2017 and March 2018 were modeled using artificial neural networks and the performance of estimating daily total global solar radiation values of the common models in the literature was investigated. Daily average air temperature, relative humidity, wind speed, sunshine duration, and cloud cover data are obtained from the Turkish State Meteorological Service and solar radiation values are measured with a pyranometer. As a result, Model 37 (Zhang and Huang) showed the best prediction performance among the models examined, with the coefficient of determination (R2) being 0.83.
Authors and Affiliations
Gökhan ARSLAN, Burhan BAYHAN, Kaan YAMAN
Keywords
Related Articles
- EP ID EP491391
- DOI 10.29109/gujsc.419473
- Views 89
- Downloads 0
Development of an M2M Platform with a Responsive Design
Nowadays it has been clearly observed that machines are more and more communicating with each other. An M2M (Machine to Machine) communication application developed for any sector needs an M2M platfrom in order to intera...
Design and Implementation of Automation System for Water Leakage Test in Vehicle
In this study, design and implementation of automation system for water leakage test, which is one of the quality control tests, in vehicle is explained in detail in order to ensure continuous operation and without inter...
Functionally Graded Porous Implants Obtained by Additive Manufacturing
Porous structures have an increasing use in the biomedical industry due to their advantage, such as supporting tissue regeneration for implants and prostheses used in the body, eliminating stress shielding and aseptic lo...
The Definition and Prediction of Stress Analysis of Plates with Elliptic Hole by Artificial Neural Networks
In this study, maximum tensile stress values on plates with elliptic hole which are exposed to tensile strength have been calculated. These calculations have been modelled by Artificial Neural Networks (ANN). Besides, fi...
A Multi Objective Genetic Algorithm Approach for The Solution of Vehicle Routing Problem with Time Windows
In this study, Vehicle Routing Problem with Time Windows (VRPTW) which is a type of classical Vehicle Routing Problem (VRP) includes customers with known demands, a single depot with known location and a certain number o...