Modeling of solar radiation using cascade-forward back-propagation neural network
| dc.contributor.advisor | Khatib , Tamer | |
| dc.contributor.author | Athamni, Abdelkader | |
| dc.contributor.author | Yaseen, Ahmad | |
| dc.contributor.author | Alawni, Ghaith | |
| dc.contributor.author | Odeh, Moataz | |
| dc.date.accessioned | 2017-10-31T08:51:41Z | |
| dc.date.available | 2017-10-31T08:51:41Z | |
| dc.date.issued | 2017 | |
| dc.description.abstract | The use of solar energy in the electricity generation and solar water heating becomes larger and larger with the passage of time as a result the need of a good solar system design is a key issue. The first requirement of any energy system design is the determination of the energy source amount. While in our case the solar radiation data represents this amount we need measuring devices to satisfy this goal. At the same time the obstacles of high cost and the intermittent solar data due to technical problems are limiting the ability of these devices, so new method is required to deal with these problems. This project introduce a high accuracy model called Cascade-Forward Backpropagation neural network(CFNN) that can predicts both the global and diffuse solar radiation also it can be used to make a restoration process for missed solar data. This model which built with special Matlab codes simply consists of three main parts: inputs, hidden layers and the output. Inputs include the hourly data of temperature, sunshine ratio and the humidity for the targeted location. Hidden layers are the processors of the previous inputs, while the output is the hourly diffuse and global solar radiation data. The evaluation process includes using MABE, RMSE, MBE statistical errors and this process proved the high accuracy of this model and the ability to use it in the solar systems design. | en_US |
| dc.identifier.uri | https://hdl.handle.net/20.500.11888/10510 | |
| dc.title | Modeling of solar radiation using cascade-forward back-propagation neural network | en_US |
| dc.type | Graduation Project | en_US |