Hybridní lineární stochastický předpovědní model pro řízení zásobní funkce nádrže

Hybrid linear stochastic forecasting model for controling storage function of water reservoire

článek ve sborníku ve WoS nebo Scopus

čeština

Průběh náhodného procesu lze lépe popsat pomocí stochastických metod než deterministických. Průměrný měsíční průtok vody v měrném profilu lze považovat za náhodný proces. Článek popisuje konstrukci a vyhodnocení hybridního předpovědního modelu pro průměrné měsíční průtoky vycházejícího z kombinace lineárního a zonálního modelu. K vyhodnocení modelu byla použita aplikace jeho výsledků na řízení zásobní funkce nádrže. Výsledky řízení byly porovnány s výsledky řízení, které používalo, jako předpověd’ výseky z reálné průtokové řady.

The main advantage of stochastic forecasting is fan of possible value, which deterministic method of forecasting could not give us. Future development of random process is described better by stochastic then deterministic forecasting. Discharge in measurement profile could be categorized as random process. Content of article is construction and application of forecasting model for managed large open water reservoir with supply function. Hybrid model is based on combination of autoregressive linear and zone models. The model forecast values of average monthly flow from combination of historic values of average monthly flow and random numbers. Part of data was sorted to one moving zone. The zone is created around last measurement average monthly flow. Matrix of correlation was assembled only from data belonging to zone. Regressive coefficients are computed by Yule-Worker equations (Yule, 1927 and Worker, 1931). The model was compiled for forecast of 1 to 12 month with using backward month flows from 2 to 11 months for model construction. Data was got ridded of asymmetry with help of Box-Cox rule (Box, Cox, 1964), value r was found by optimization. In next step were data transform to standard normal distribution. The data were with monthly step and forecast is recurring. 90 years long real flow series was used for compile of the model. First 75 years were used for calibration of model (matrix input-output relationship), last 15 years were used only for validation. Outputs of model were compared with real flow series. For comparison between real flow series (100% successfully of forecast) and forecasts, was used application to management of artificially made reservoir. Course of water reservoir management using Genetic algorithm (GE) + real flow series was compared with Fuzzy model (Fuzzy) + forecast made by hybrid model. During evaluation process was founding the best size of zone. Results show that the highest number of input did not give the best results and ideal size of zone is in interval from 10 to 15, when course of management was almost same for all numbers from interval. Resulted course of management was compared with course, which was obtained from using GE + real flow series. Comparing results showed that fuzzy model with forecasted values has been able to manage main malfunction and artificially disorders made by model were founded essential, after values of water volume during management were evaluated. Forecasting model in combination with fuzzy model provide very good results in management of water reservoir with storage function and can be recommended for this purpose.

Zásobní funkce, předpověď, průměrný měsíční průtok

Storage function, forecast, average monthly flow

KOZEL, T.

9. 11. 2017

Slovenský hydrometeorologický ústav

Bratislava

978-80-88907-95-4

Zborník súťažných prác mladých odborníkov

100

108

8