Análise e Comparação de Modelos de Previsão de Vazões para o Planejamento Energético, Utilizando Séries Temporais
Saved in:
| Main Author: | |
|---|---|
| Publication Date: | 2009 |
| Format: | Master thesis |
| Language: | por |
| Source: | Repositório Institucional da UFG |
| Download full: | http://repositorio.bc.ufg.br/tede/handle/tde/994 |
Summary: | n the planning of the energetic operation, analysis and forecasts of the flow are very important. A huge difficulty in the forecast of flow is the seasonality presence, due to drought and flood periods in the year. Many scientists, with different methodologies, have been concerned with finding a best model, compared with the utilized by Brazil s system - Markovian Model. The Makovian Model, or selfregressive with order 1, is a Box & Jenkins methodology, and requires data handling to treat non-stationarity, or the use of regular models, requiring a hardly theoretical formulation for the statistical procedures. Therefore, the statistical models, autoregressive model with seasonality and Holt-Winters model, of treatment of temporal series are presented and, carried out the flow s analysis and forecast for three study groups, in two different (historical) horizons. The performance of the models was compared and the results showed that the proposed models presents better adjust than the model adopted by Brazilian system |
Similar Items: Análise e Comparação de Modelos de Previsão de Vazões para o Planejamento Energético, Utilizando Séries Temporais
- Um modelo híbrido para séries temporais hierárquicas com múltipla sazonalidade
- Previsão de séries temporais : extensão sazonal e bagging para o Modelo Theta Otimizado
- Aprendizagem cruzada para previsão de séries temporais univariadas
- Previsão de séries temporais aplicada a dados de venda de uma grande varejista do Brasil.
- Uso de séries temporais do sensor MODIS para identificar diferentes culturas agrícolas
- Previsão do PIB estadual : novos concorrentes versus modelos tradicionais de séries temporais