The Sunshine Duration Error Rates were calculated with Gradient-Descent Algorithm and Genetic Algorithm for Use of Solar Energy
Journal Title: International Scientific and Vocational Studies Journal - Year 2017, Vol 1, Issue 1
Abstract
In this study, which is a source of renewable energy required to take advantage of solar energy to the maximum duration of sunshine was estimated. In the study, values were used of the city of Amasya. Artificial neural networks (ANN) backpropagation gradient-descent(GD) learn algorithm and genetic algorithm(GA) were used. Three hidden layer network model was designed with two inputs for ANN and GA. Between 2000 and 2010 values were used as input data monthly sunshine duration and humidity values. Output data was obtained monthly sunshine duration of 2010. The values obtained were compared with the actual values and the root mean square error (RMSE) was calculated. Result of the study, GA was used to calculate the values that are needed for solar energy.
Authors and Affiliations
Yalçın KAPLAN
Removal of Major Impurties (Ca-Mg) of Brine with Chemical Treatment Process in the Salt Sector
The operation of salt minerals dates back hundreds of years. Salt is produced from salt rich sources through salts today. The salt (brine) obtained from existing salt sources is not in the desired purity. For this purpos...
Exterior Scaffolds of Prefabricated Components, Loads Affecting Scaffolds and Scaffold Experiments
In the construction sector, constructions, painting, heat insulation, coating and so on. Outside facade scaffoldings are widely used in outdoor facade applications. The floats consist of temporary elements which are des...
Analytical Design of PI Controllers for First Order plus Time Delay Systems
This study proposes an analytical design method of a Proportional Integral controller for the stability and performance of first order plus time delay systems. The method proposed in the study achieves general computatio...
Solar Cell Usage in a House in Erdemli District of Mersin for Meeting Electricity Demand and Cost Analysis
Energy is the one of the basic needs in order to survive since human existence. The vast majority of this energy is derived from fosil fuels. The increase in energy demand, the limited resources, and harmful effect of di...
Thermal Stress Control in Functionally Graded Plates with Artificial Neural Network
In this study, trained models were obtained by using Artificial Neural Network (ANN) in order to determine the equivalent stress levels of one dimensional functionally graded rectangular plates. In this training set, a...