FUZZY INFERENCE SYSTEMS FOR MULTI-STEP AHEAD DAILY INFLOW FORECASTING

Autor(es)

Ivette Luna ^[1] ; Ieda G. Hidalgo ^[2] ; Paulo S.M. Pedro ^[3] ; Paulo S.F. Barbosa ^[4] ; Alberto L. Francato ^[5] ; Paulo B. Correia ^[6]

Afiliação do(s) autor(es)

^[1] Universidade Estadual de Campinas. Instituto de Economia - Brasil

^[2] Universidade Estadual de Campinas. Faculdade de Tecnologia - Brasil

^[3] Universidade Estadual de Campinas. Faculdade de Tecnologia - Brasil

^[4] Universidade Estadual de Campinas. Faculdade de Engenharia Civil, Arquitetura e Urbanismo - Brasil

^[5] Universidade Estadual de Campinas. Faculdade de Engenharia Civil, Arquitetura e Urbanismo - Brasil

^[6] Universidade Estadual de Campinas. Faculdade de Engenharia Mecânica - Brasil

• Tipo de documento: Artigo Científico
• Fonte: Pesquisa Operacional; v. 37, n. 1, p. 129-144, 2017-01-00.

Resumo

ABSTRACT This paper presents the evaluation of a daily inflow forecasting model using a tool that facilitates the analysis of mathematical models for hydroelectric plants. The model is based on a Fuzzy Inference System. An offline version of the Expectation Maximization algorithm is employed to adjust the model parameters. The tool integrates different inflow forecasting models into a single physical structure. It makes uniform and streamlines the management of data, prediction studies, and presentation of results. A case study is carried out using data from three Brazilian hydroelectric plants of the Parana basin, Tiete River, in southern Brazil. Their activities are coordinated by Operator of the National Electric System (ONS) and inspected by the National Agency for Electricity (ANEEL). The model is evaluated considering a multi-step ahead forecasting task. The graphs allow a comparison between observed and forecasted inflows. For statistical analysis, it is used the mean absolute percentage error, the root mean square error, the mean absolute error, and the mass curve coefficient. The results show an adequate performance of the model, leading to a promising alternative for daily inflow forecasting. (AU)

• Processo FAPESP: 11/09178-1 - Gerenciamento de estudos de previsão de vazões com módulo de consultas avançadas
• Beneficiário: Ieda Geriberto Hidalgo
• Modalidade de apoio: Auxílio à Pesquisa - Regular