Forecasting model for the change in stage of reservoir water level
Reservoir is one of major structural approaches for flood mitigation. During floods, early reservoir water release is one of the actions taken by the reservoir operator to accommodate incoming heavy rainfall. Late water release might give negative effect to the reservoir structure and cause flood at...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | eng eng |
| Published: |
2016
|
| Subjects: | |
| Online Access: | https://etd.uum.edu.my/6033/1/s814388_01.pdf https://etd.uum.edu.my/6033/2/s814388_02.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Reservoir is one of major structural approaches for flood mitigation. During floods, early reservoir water release is one of the actions taken by the reservoir operator to accommodate incoming heavy rainfall. Late water release might give negative effect to the reservoir structure and cause flood at downstream area. However, current rainfall may not directly influence the change of reservoir water level. The delay may occur as the streamflow that carries the water might take some time to reach the reservoir. This study is aimed to develop a forecasting model for the change in stage
of reservoir water level. The model considers the changes of reservoir water level and its stage as the input and the future change in stage of reservoir water level as the output. In this study, the Timah Tasoh reservoir operational data was obtained from the Perlis Department of Irrigation and Drainage (DID). The reservoir water level
was categorised into stages based on DID manual. A modified sliding window algorithm has been deployed to segment the data into temporal patterns. Based on the patterns, three models were developed: the reservoir water level model, the change of reservoir water level and stage of reservoir water level model, and the combination of the change of reservoir water level and stage of reservoir water level model. All models were simulated using neural network and their performances were compared using on mean square error (MSE) and percentage of correctness. The result shows that the change of reservoir water level and stage of reservoir water
model produces the lowest MSE and the highest percentage of correctness when compared to the other two models. The findings also show that a delay of two previous days has affected the change in stage of reservoir water level. The model
can be applied to support early reservoir water release decision making. Thus, reduce the impact of flood at the downstream area. |
|---|