1 AIT Asian Institute of Technology

Prediction of inflow to Buon Tua Srah Reservoir, Vietnam

AuthorVo Trong Son
Call NumberAIT Thesis no.WM-06-7
Subject(s)Streamflow--Vietnam--Buon Tua Srah Reservoir--Forecasting
Rain and rainfall--Vietnam--Buon Tua Srah Reservoir--Forecasting

NoteA thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Water Engineering and Management
PublisherAsian Institute of Technology
AbstractAccurate forecast of inflow to reservoir is of particular interest for reservoir operation and scheduling. For hydropower reservoir equipped with control gates, improved criteria for gates operation can be assessed if reliable forecast of inflow to the reservoir is available. Prediction of rainfall should be considered for extension of lead-time of discharge forecast. This study presents three folds. Firstly, the application of the Artificial Neural Network (ANN) model and Nam model for daily inflow forecast. Secondly, the application of the Singular-Spectrum Analysis (SSA) with Principle Component Analysis technique and the Artificial Neural Network (ANN) model for 1day and 2days ahead rainfall forecast. Thirdly, the application of ANN model for lday ahead, 2days ahead and 3days ahead discharge forecasting using forecast of rainfall and streamflow. Besides, the combination of Deterministic model and Stochastic model (BPNN+ AR(3)) is used to improve the efficiency of results. The ANN model (WinNN32) has been applied for daily rainfall forecast based on the Singular-Spectrum Analysis (SSA) with Principle Component Analysis technique. The ANN model cannot be directly applied to forecast discontinuous signals, like rainfall time series, as the universal function approximation theorems for neural networks system that requires the continuity of the function to be approximated. In order to avoid the effect of discontinuous of a signal, the SSA technique is applied to forecast the signal by decomposing the raw rainfall time series into reconstructed components. Then, reconstructed components are simulated by ANN to obtain rainfall time series forecast for several lead-times (1day and 2days respectively). After that, rainfall forecast is obtained as inputs for prediction of inflow to the Buon Tua Srah reservoir at Due Xuyen station. The results of the forecast of inflow to Buon Tua Srah reservoir at Due Xuyen station are found to be satisfactory for lead time from 1day to 3days.
Year2007
TypeThesis
SchoolSchool of Engineering and Technology (SET)
DepartmentDepartment of Civil and Infrastucture Engineering (DCIE)
Academic Program/FoSWater Engineering and Management (WM)
Chairperson(s)Tawatchai Tingsanchali;
Examination Committee(s)Clemente, Roberto S.;Sutat Weesakul;Vilas Nitivattananon;
Scholarship Donor(s)Electricity of Vietnam (EVN);AIT Fellowship;
DegreeThesis (M.Eng.) - Asian Institute of Technology, 2007


Usage Metrics
View Detail0
Read PDF0
Download PDF0