Premium
Short‐term prediction of water flow data into hydroelectric power stations using local fuzzy reconstruction method
Author(s) -
Iokibe Tadashi,
Yonezawa Yoshitsugu,
Taniguchi Minako
Publication year - 2000
Publication title -
electrical engineering in japan
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.136
H-Index - 28
eISSN - 1520-6416
pISSN - 0424-7760
DOI - 10.1002/(sici)1520-6416(200003)130:4<99::aid-eej11>3.0.co;2-2
Subject(s) - hydroelectricity , inflow , term (time) , artificial neural network , fuzzy logic , computer science , power (physics) , flow (mathematics) , nonlinear system , engineering , meteorology , artificial intelligence , mathematics , electrical engineering , physics , geometry , quantum mechanics
For predicting the flow into a hydroelectric power station, complex natural phenomena have to be dealt with, so conventional mathematical models based on hydraulics may not produce satisfactory results. When a neural network is used, its construction cannot be easily determined, and extra neural networks must be provided separately in addition to the normal neural network, according to experts' opinions about the problem. To solve these problems, the authors took the standpoint that if the inflow rate time‐series data for hydroelectric power stations exhibit deterministic chaos, the status in the near future can be predicted. Thus, the authors have applied the local fuzzy reconstruction method as a deterministic nonlinear short‐term prediction method to data for the flow of water into hydroelectric power stations. In this paper, typical outflow analysis method using conventional mathematical models is first described briefly. Next, the “Local Fuzzy Reconstruction Method” is described. Third, chaotic behavior of water flow data into hydroelectric power stations is illustrated. Finally, the results of applying the method to the prediction of the flow into hydroelectric power stations are presented. © 2000 Scripta Technica, Electr Eng Jpn, 130(4): 99–106, 2000