No description available.

Stochastic control of large open water reservior stock fiction with operates a given variance of flow values a certain probability distribution. Stochastic forecasting models for stochastic management were compiled as part of the thesis. The stochastic procedure has the choice of the procedur efor a certain probability scenário as aópposed to the deterministic procedure. The probability election is provided by a fan of options. The thesis deals with the construction and subsequent evalution of stochastic management of the reservoir fiction. Using stochastic models management was performed with some probability of exceeding the controlled watr outflow from the large open water reservior. The simulation took place an a fictional large open water reservior. Subsequently a comparsion was made between management using individual methods and using forecats. Stochastic kontrol performed the large open water reservoir´s stock fiction well. At the end of the diploma thesis the best settings for each forecast and kontrol model were selected.

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. We can categorize discharge in measurement profile as random process. Stochastic management is worked with dispersion of controlling discharge value. In thesis is described construction and evaluation of adaptive stochastic model base on fuzzy logic, neural networks and evolution algorithm, which are used stochastic forecast from forecasting models described in thesis. The learning fuzzy model and neural network is used as replacement of classic optimization algorithm (evolution algorithm). Model was tested and validated on made up large open water reservoir. Results were evaluated and were compared with model base on traditional algorithms, which was used for 100% forecast (forecasted values are real values). The management of the large open water reservoir with storage function, which was given by stochastic adaptive managing, was logical. The main advantage of fuzzy model and neural network model is computing speed. Classical optimization model is needed much more time for same calculation as fuzzy and neural network model, therefore classic model used clusters for stochastic calculation.

The diploma thesis is focused on the long term prediction of mean monthly flows in hydrometric profile for purposes of reservoir control optimization and optimization of reservoir systems. Discharges were predicted using by artificial neural network method. Predicted flows were statistically evaluated by relevant coefficients and then compared with the measured flows for given river hydrometric profiles.