| Grant number: | 13/03853-4 |
| Support Opportunities: | Regular Research Grants |
| Start date: | November 01, 2013 |
| End date: | October 31, 2015 |
| Field of knowledge: | Engineering - Electrical Engineering - Power Systems |
| Principal Investigator: | Anna Diva Plasencia Lotufo |
| Grantee: | Anna Diva Plasencia Lotufo |
| Host Institution: | Faculdade de Engenharia (FEIS). Universidade Estadual Paulista (UNESP). Campus de Ilha Solteira. Ilha Solteira , SP, Brazil |
Abstract
Knowing in advance the variables of the electrical power systems as well as other engineering systems is very important. The use of neural networks for problems that are difficult to model becomes an easier task. Recently the use o hybrid models with neural networks and ARIMA of Box&Jenkins brings good results exploring the advantages of one and other. This project intends to develop some software to predict load, stream flow and prices. Load forecasting is going to use ARIMA of Box&Jenkins (for linear part) and ART family neural network (for nonlinear part). The stream flow prediction will use an ART family neural network and the same one for the prices also including the GRNN from MATLAB. The results will be compared from benchmarks of the literature, as well as other results developed by the neural network group. (AU)
| Articles published in Agência FAPESP Newsletter about the research grant: |
| More itemsLess items |
| TITULO |
| Articles published in other media outlets ( ): |
| More itemsLess items |
| VEICULO: TITULO (DATA) |
| VEICULO: TITULO (DATA) |