|
|
Construction of forecast model for water flow in the measurement profile
Škarecký, Pavel ; BBA, Šárka Zemanová, (referee) ; Kozel, Tomáš (advisor)
The subject of this bachelor thesis was the construction and calibration of a prediction model for water flow in a specific profile on the river Dyje in the village Podhradí nad Dyjí. The work is divided into theoretical and computational part. The theoretical part describes the transformation of historical data, types of probabilistic models and current drought problems. The computational part describes the stochastic model, the distribution of flows into zones of occurrence and the subsequent determination of the ideal quantile. Finally, the individual settings of the model and the evaluation of the results are compared.
|
|
|
Stochastic management of water reservoir storage function
Pruch, David ; Matoušek, Petr (referee) ; Kozel, Tomáš (advisor)
The stochastic control of the reservoir storage function works with a certain number of control flow values with a certain probability distribution. For the requirement of stochastic control of the reservoir storage function, a stochastic prediction model based on the LHS method was compiled. The model works with random processes, which include flow in a specific measurement profile. Stochastic control has the advantage over deterministic control in the possibility of selecting a control for a particular probability scenario. Some deterministic methods as well as some stochastic methods are described very briefly. Furthermore, the thesis describes the procedure for the control of the reservoir storage function using the LHS method. The model was tested on a fictitious reservoar. In conclusion, the best and worst results were selected, which were then compared, so it could be determined which parametrs of calculation was most ideal for driving.
|
|
|
Use of artificial intelligence methods for flow prediction in specific profile
Škarecký, Pavel ; BBA, Šárka Zemanová, (referee) ; Kozel, Tomáš (advisor)
The subject of this diploma thesis was the construction and calibration of a forecast model for water flow in the specific profile on the river Dyje in the village Podhradí nad Dyjí. The description of the theoretical part describes various prediction models and description of the prediction model using the technique of random walking and a description of neural networks. The practical part was then devoted to the description of the locality of interest, the creation of a prediction model and the use of neural networks as post processing to improve the results.
|
|
|
Stochastic management storage function of water reservoir using method of artificial intelligence
Kozel, Tomáš ; Fošumpaur, Pavel (referee) ; Zezulák,, Jiří (referee) ; Starý, Miloš (advisor)
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.
|
|
|
Forecasting model for forecast of flows in measured profile
Urbanec, Patrik ; Matoušek, Petr (referee) ; Kozel, Tomáš (advisor)
The subject of this bachelor thesis was the compilation and calibration of the prediction model of water flow in the specific profile of Bílovice nad Svitou on the Svitavy River and its evaluation. The thesis is divided into the calculation part and the theoretical part. In the calculation part is described a model based on neural networks and its calibration. Furthermore, the evaluation of predictions using histograms, averages and median frequencies for each month is described in the paper. The theoretical part describes neural networks, methodology and evaluation of results from the calculation part. Finally, we compare each neural network setting. Based on the results obtained, the predictive model can be recommended for further investigation.
|
|
|
Use of artificial intelligence methods for flow prediction in specific profile
Škarecký, Pavel ; BBA, Šárka Zemanová, (referee) ; Kozel, Tomáš (advisor)
The subject of this diploma thesis was the construction and calibration of a forecast model for water flow in the specific profile on the river Dyje in the village Podhradí nad Dyjí. The description of the theoretical part describes various prediction models and description of the prediction model using the technique of random walking and a description of neural networks. The practical part was then devoted to the description of the locality of interest, the creation of a prediction model and the use of neural networks as post processing to improve the results.
|
|
|
Construction of forecast model for water flow in the measurement profile
Škarecký, Pavel ; BBA, Šárka Zemanová, (referee) ; Kozel, Tomáš (advisor)
The subject of this bachelor thesis was the construction and calibration of a prediction model for water flow in a specific profile on the river Dyje in the village Podhradí nad Dyjí. The work is divided into theoretical and computational part. The theoretical part describes the transformation of historical data, types of probabilistic models and current drought problems. The computational part describes the stochastic model, the distribution of flows into zones of occurrence and the subsequent determination of the ideal quantile. Finally, the individual settings of the model and the evaluation of the results are compared.
|
|
|
Stochastic management of water reservoir storage function
Pruch, David ; Matoušek, Petr (referee) ; Kozel, Tomáš (advisor)
The stochastic control of the reservoir storage function works with a certain number of control flow values with a certain probability distribution. For the requirement of stochastic control of the reservoir storage function, a stochastic prediction model based on the LHS method was compiled. The model works with random processes, which include flow in a specific measurement profile. Stochastic control has the advantage over deterministic control in the possibility of selecting a control for a particular probability scenario. Some deterministic methods as well as some stochastic methods are described very briefly. Furthermore, the thesis describes the procedure for the control of the reservoir storage function using the LHS method. The model was tested on a fictitious reservoar. In conclusion, the best and worst results were selected, which were then compared, so it could be determined which parametrs of calculation was most ideal for driving.
|
|
|
Stochastic management storage function of water reservoir using method of artificial intelligence
Kozel, Tomáš ; Fošumpaur, Pavel (referee) ; Zezulák,, Jiří (referee) ; Starý, Miloš (advisor)
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.
|
|
|
Forecasting model for forecast of flows in measured profile
Urbanec, Patrik ; Matoušek, Petr (referee) ; Kozel, Tomáš (advisor)
The subject of this bachelor thesis was the compilation and calibration of the prediction model of water flow in the specific profile of Bílovice nad Svitou on the Svitavy River and its evaluation. The thesis is divided into the calculation part and the theoretical part. In the calculation part is described a model based on neural networks and its calibration. Furthermore, the evaluation of predictions using histograms, averages and median frequencies for each month is described in the paper. The theoretical part describes neural networks, methodology and evaluation of results from the calculation part. Finally, we compare each neural network setting. Based on the results obtained, the predictive model can be recommended for further investigation.
|
guest ::
